Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1645 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1393. Min Range: -5.1393
Max Act: 5.1393. Min Act: -0.1700
Data Index: 6257197 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1393. Min Range: -5.1393
Max Act: 5.1081. Min Act: -0.1700
Data Index: 4803070 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1393. Min Range: -5.1393
Max Act: 5.1081. Min Act: -0.1700
Data Index: 7680972 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1393. Min Range: -5.1393
Max Act: 4.9518. Min Act: -0.1700
Data Index: 8283357 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1393. Min Range: -5.1393
Max Act: 4.9206. Min Act: -0.1700
Data Index: 4523793 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1393. Min Range: -5.1393
Max Act: 4.8581. Min Act: -0.1700
Data Index: 2582225 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1393. Min Range: -5.1393
Max Act: 4.7956. Min Act: -0.1700
Data Index: 1562005 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1393. Min Range: -5.1393
Max Act: 4.8268. Min Act: -0.1700
Data Index: 7467186 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1393. Min Range: -5.1393
Max Act: 4.8268. Min Act: -0.1700
Data Index: 758560 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1393. Min Range: -5.1393
Max Act: 4.7956. Min Act: -0.1700
Data Index: 1701968 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1393. Min Range: -5.1393
Max Act: 4.7956. Min Act: -0.1700
Data Index: 3365956 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1393. Min Range: -5.1393
Max Act: 4.7643. Min Act: -0.1700
Data Index: 2770848 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1393. Min Range: -5.1393
Max Act: 4.7956. Min Act: -0.1700
Data Index: 1117581 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1393. Min Range: -5.1393
Max Act: 4.7956. Min Act: -0.1700
Data Index: 1928580 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1393. Min Range: -5.1393
Max Act: 4.7956. Min Act: -0.1700
Data Index: 4429140 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1393. Min Range: -5.1393
Max Act: 4.7956. Min Act: -0.1700
Data Index: 4173912 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1393. Min Range: -5.1393
Max Act: 4.7956. Min Act: -0.1700
Data Index: 6076160 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1393. Min Range: -5.1393
Max Act: 4.7643. Min Act: -0.1700
Data Index: 2617822 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1393. Min Range: -5.1393
Max Act: 4.7331. Min Act: -0.1700
Data Index: 4290306 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1393. Min Range: -5.1393
Max Act: 4.7643. Min Act: -0.1700
Data Index: 7692401 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #19