Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 391 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.5256. Min Range: -2.5256
Max Act: 2.5256. Min Act: -0.1700
Data Index: 5299206 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5256. Min Range: -2.5256
Max Act: 2.4932. Min Act: -0.1700
Data Index: 5399930 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5256. Min Range: -2.5256
Max Act: 2.5094. Min Act: -0.1700
Data Index: 5299208 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5256. Min Range: -2.5256
Max Act: 2.4770. Min Act: -0.1700
Data Index: 834081 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5256. Min Range: -2.5256
Max Act: 2.4770. Min Act: -0.1700
Data Index: 6475919 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5256. Min Range: -2.5256
Max Act: 2.4770. Min Act: -0.1700
Data Index: 5704350 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5256. Min Range: -2.5256
Max Act: 2.4932. Min Act: -0.1700
Data Index: 369481 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5256. Min Range: -2.5256
Max Act: 2.4770. Min Act: -0.1700
Data Index: 6616602 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5256. Min Range: -2.5256
Max Act: 2.4445. Min Act: -0.1700
Data Index: 8520392 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5256. Min Range: -2.5256
Max Act: 2.4607. Min Act: -0.1700
Data Index: 8783728 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5256. Min Range: -2.5256
Max Act: 2.4282. Min Act: -0.1700
Data Index: 4607515 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5256. Min Range: -2.5256
Max Act: 2.4445. Min Act: -0.1700
Data Index: 294967 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5256. Min Range: -2.5256
Max Act: 2.4282. Min Act: -0.1700
Data Index: 6534295 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5256. Min Range: -2.5256
Max Act: 2.4282. Min Act: -0.1700
Data Index: 2103285 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5256. Min Range: -2.5256
Max Act: 2.4119. Min Act: -0.1700
Data Index: 3737707 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5256. Min Range: -2.5256
Max Act: 2.3793. Min Act: -0.1700
Data Index: 7039263 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5256. Min Range: -2.5256
Max Act: 2.3629. Min Act: -0.1700
Data Index: 926383 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5256. Min Range: -2.5256
Max Act: 2.3629. Min Act: -0.1700
Data Index: 3629705 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5256. Min Range: -2.5256
Max Act: 2.3629. Min Act: -0.1700
Data Index: 8295788 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5256. Min Range: -2.5256
Max Act: 2.3465. Min Act: -0.1700
Data Index: 1254605 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #19