Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1451 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4650. Min Range: -4.4650
Max Act: 4.4650. Min Act: -0.1700
Data Index: 1821237 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4650. Min Range: -4.4650
Max Act: 4.3400. Min Act: -0.1700
Data Index: 2413500 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4650. Min Range: -4.4650
Max Act: 4.3088. Min Act: -0.1700
Data Index: 6805386 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4650. Min Range: -4.4650
Max Act: 4.2775. Min Act: -0.1700
Data Index: 884840 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4650. Min Range: -4.4650
Max Act: 4.2463. Min Act: -0.1700
Data Index: 7649888 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4650. Min Range: -4.4650
Max Act: 4.1525. Min Act: -0.1700
Data Index: 3170667 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4650. Min Range: -4.4650
Max Act: 4.1525. Min Act: -0.1700
Data Index: 2446843 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4650. Min Range: -4.4650
Max Act: 4.1212. Min Act: -0.1700
Data Index: 645571 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4650. Min Range: -4.4650
Max Act: 4.0900. Min Act: -0.1700
Data Index: 7438714 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4650. Min Range: -4.4650
Max Act: 4.0900. Min Act: -0.1700
Data Index: 579559 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4650. Min Range: -4.4650
Max Act: 4.0587. Min Act: -0.1700
Data Index: 4759413 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4650. Min Range: -4.4650
Max Act: 4.0587. Min Act: -0.1700
Data Index: 8720173 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4650. Min Range: -4.4650
Max Act: 4.0275. Min Act: -0.1700
Data Index: 1097561 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4650. Min Range: -4.4650
Max Act: 3.9962. Min Act: -0.1700
Data Index: 5430094 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4650. Min Range: -4.4650
Max Act: 3.9962. Min Act: -0.1700
Data Index: 7592431 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4650. Min Range: -4.4650
Max Act: 3.9962. Min Act: -0.1700
Data Index: 1404413 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4650. Min Range: -4.4650
Max Act: 3.9337. Min Act: -0.1700
Data Index: 7229848 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4650. Min Range: -4.4650
Max Act: 3.9337. Min Act: -0.1700
Data Index: 5430095 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4650. Min Range: -4.4650
Max Act: 3.9024. Min Act: -0.1700
Data Index: 3949914 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4650. Min Range: -4.4650
Max Act: 3.9024. Min Act: -0.1700
Data Index: 5877232 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #19