Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4657 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7995. Min Range: -5.7995
Max Act: 5.7995. Min Act: -0.1700
Data Index: 4654731 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7995. Min Range: -5.7995
Max Act: 5.7370. Min Act: -0.1700
Data Index: 7944536 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7995. Min Range: -5.7995
Max Act: 5.7682. Min Act: -0.1700
Data Index: 3936121 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7995. Min Range: -5.7995
Max Act: 5.7370. Min Act: -0.1700
Data Index: 5578790 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7995. Min Range: -5.7995
Max Act: 5.7370. Min Act: -0.1700
Data Index: 2634203 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7995. Min Range: -5.7995
Max Act: 5.7370. Min Act: -0.1700
Data Index: 5727134 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7995. Min Range: -5.7995
Max Act: 5.7370. Min Act: -0.1700
Data Index: 3206433 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7995. Min Range: -5.7995
Max Act: 5.7370. Min Act: -0.1700
Data Index: 5319242 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7995. Min Range: -5.7995
Max Act: 5.7057. Min Act: -0.1700
Data Index: 2564511 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7995. Min Range: -5.7995
Max Act: 5.7057. Min Act: -0.1700
Data Index: 674387 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7995. Min Range: -5.7995
Max Act: 5.7057. Min Act: -0.1700
Data Index: 4299500 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7995. Min Range: -5.7995
Max Act: 5.7057. Min Act: -0.1700
Data Index: 5135531 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7995. Min Range: -5.7995
Max Act: 5.6745. Min Act: -0.1700
Data Index: 4048568 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7995. Min Range: -5.7995
Max Act: 5.6745. Min Act: -0.1700
Data Index: 4137051 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7995. Min Range: -5.7995
Max Act: 5.6745. Min Act: -0.1700
Data Index: 2570838 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7995. Min Range: -5.7995
Max Act: 5.6745. Min Act: -0.1700
Data Index: 1191143 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7995. Min Range: -5.7995
Max Act: 5.6432. Min Act: -0.1700
Data Index: 7403281 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7995. Min Range: -5.7995
Max Act: 5.6120. Min Act: -0.1700
Data Index: 5474151 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7995. Min Range: -5.7995
Max Act: 5.6120. Min Act: -0.1700
Data Index: 2868548 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7995. Min Range: -5.7995
Max Act: 5.6120. Min Act: -0.1700
Data Index: 732283 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #19