Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2495 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 12.4650. Min Range: -12.4650
Max Act: 12.4650. Min Act: -0.1700
Data Index: 2049309 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.4650. Min Range: -12.4650
Max Act: 12.2150. Min Act: -0.1700
Data Index: 6442204 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.4650. Min Range: -12.4650
Max Act: 12.0900. Min Act: -0.1700
Data Index: 578028 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.4650. Min Range: -12.4650
Max Act: 12.0900. Min Act: -0.1700
Data Index: 5341558 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.4650. Min Range: -12.4650
Max Act: 12.0900. Min Act: -0.1700
Data Index: 2507827 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.4650. Min Range: -12.4650
Max Act: 12.0900. Min Act: -0.1700
Data Index: 8831862 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.4650. Min Range: -12.4650
Max Act: 12.0900. Min Act: -0.1700
Data Index: 8831860 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.4650. Min Range: -12.4650
Max Act: 12.0275. Min Act: -0.1700
Data Index: 8831861 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.4650. Min Range: -12.4650
Max Act: 11.9025. Min Act: -0.1700
Data Index: 3962756 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.4650. Min Range: -12.4650
Max Act: 11.8400. Min Act: -0.1700
Data Index: 5944170 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.4650. Min Range: -12.4650
Max Act: 11.7775. Min Act: -0.1700
Data Index: 7504307 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.4650. Min Range: -12.4650
Max Act: 11.7775. Min Act: -0.1700
Data Index: 2471533 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.4650. Min Range: -12.4650
Max Act: 11.7775. Min Act: -0.1700
Data Index: 5402544 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.4650. Min Range: -12.4650
Max Act: 11.7150. Min Act: -0.1700
Data Index: 4757475 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.4650. Min Range: -12.4650
Max Act: 11.7150. Min Act: -0.1700
Data Index: 1155336 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.4650. Min Range: -12.4650
Max Act: 11.7150. Min Act: -0.1700
Data Index: 8463059 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.4650. Min Range: -12.4650
Max Act: 11.7150. Min Act: -0.1700
Data Index: 6053344 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.4650. Min Range: -12.4650
Max Act: 11.7150. Min Act: -0.1700
Data Index: 5869854 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.4650. Min Range: -12.4650
Max Act: 11.6525. Min Act: -0.1700
Data Index: 547992 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.4650. Min Range: -12.4650
Max Act: 11.6525. Min Act: -0.1700
Data Index: 3476208 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19