Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 596 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6276. Min Range: -4.6276
Max Act: 4.6276. Min Act: -0.1700
Data Index: 7666703 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6276. Min Range: -4.6276
Max Act: 4.5339. Min Act: -0.1700
Data Index: 6392482 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6276. Min Range: -4.6276
Max Act: 4.4089. Min Act: -0.1700
Data Index: 4305326 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6276. Min Range: -4.6276
Max Act: 4.3464. Min Act: -0.1700
Data Index: 7391469 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6276. Min Range: -4.6276
Max Act: 4.3151. Min Act: -0.1700
Data Index: 6987484 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6276. Min Range: -4.6276
Max Act: 4.3151. Min Act: -0.1700
Data Index: 4070227 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6276. Min Range: -4.6276
Max Act: 4.2526. Min Act: -0.1700
Data Index: 8301553 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6276. Min Range: -4.6276
Max Act: 4.2214. Min Act: -0.1700
Data Index: 8288775 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6276. Min Range: -4.6276
Max Act: 4.2214. Min Act: -0.1700
Data Index: 4141070 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6276. Min Range: -4.6276
Max Act: 4.1901. Min Act: -0.1700
Data Index: 3973171 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6276. Min Range: -4.6276
Max Act: 4.1901. Min Act: -0.1700
Data Index: 4963127 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6276. Min Range: -4.6276
Max Act: 4.1901. Min Act: -0.1700
Data Index: 6832293 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6276. Min Range: -4.6276
Max Act: 4.1901. Min Act: -0.1700
Data Index: 638178 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6276. Min Range: -4.6276
Max Act: 4.1589. Min Act: -0.1700
Data Index: 6386541 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6276. Min Range: -4.6276
Max Act: 4.1589. Min Act: -0.1700
Data Index: 629089 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6276. Min Range: -4.6276
Max Act: 4.1276. Min Act: -0.1700
Data Index: 4548397 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6276. Min Range: -4.6276
Max Act: 4.1276. Min Act: -0.1700
Data Index: 4758642 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6276. Min Range: -4.6276
Max Act: 4.1276. Min Act: -0.1700
Data Index: 7096044 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6276. Min Range: -4.6276
Max Act: 4.1276. Min Act: -0.1700
Data Index: 3091696 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6276. Min Range: -4.6276
Max Act: 4.0963. Min Act: -0.1700
Data Index: 5368688 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #19