Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2578 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 10.7693. Min Range: -10.7693
Max Act: 10.7693. Min Act: -0.1700
Data Index: 878951 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.7693. Min Range: -10.7693
Max Act: 10.3943. Min Act: -0.1700
Data Index: 7130033 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.7693. Min Range: -10.7693
Max Act: 10.3943. Min Act: -0.1700
Data Index: 3410398 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.7693. Min Range: -10.7693
Max Act: 10.2068. Min Act: -0.1700
Data Index: 8366171 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.7693. Min Range: -10.7693
Max Act: 10.1443. Min Act: -0.1700
Data Index: 8115571 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.7693. Min Range: -10.7693
Max Act: 10.0818. Min Act: -0.1700
Data Index: 8660018 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.7693. Min Range: -10.7693
Max Act: 10.0818. Min Act: -0.1700
Data Index: 3071483 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.7693. Min Range: -10.7693
Max Act: 10.0193. Min Act: -0.1700
Data Index: 1033148 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.7693. Min Range: -10.7693
Max Act: 10.0193. Min Act: -0.1700
Data Index: 4781091 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.7693. Min Range: -10.7693
Max Act: 10.0193. Min Act: -0.1700
Data Index: 999491 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.7693. Min Range: -10.7693
Max Act: 10.0193. Min Act: -0.1700
Data Index: 6068399 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.7693. Min Range: -10.7693
Max Act: 9.9568. Min Act: -0.1700
Data Index: 2902297 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.7693. Min Range: -10.7693
Max Act: 10.0193. Min Act: -0.1700
Data Index: 6349290 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.7693. Min Range: -10.7693
Max Act: 9.9568. Min Act: -0.1700
Data Index: 1390150 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.7693. Min Range: -10.7693
Max Act: 9.9568. Min Act: -0.1700
Data Index: 6637196 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.7693. Min Range: -10.7693
Max Act: 9.9568. Min Act: -0.1700
Data Index: 4815377 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.7693. Min Range: -10.7693
Max Act: 9.9568. Min Act: -0.1700
Data Index: 5680478 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.7693. Min Range: -10.7693
Max Act: 9.8943. Min Act: -0.1700
Data Index: 3333119 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.7693. Min Range: -10.7693
Max Act: 9.8943. Min Act: -0.1700
Data Index: 5162420 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.7693. Min Range: -10.7693
Max Act: 9.9568. Min Act: -0.1700
Data Index: 7192199 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #19