Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1145 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.1079. Min Range: -2.1079
Max Act: 2.1079. Min Act: -0.1700
Data Index: 259529 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1079. Min Range: -2.1079
Max Act: 2.0576. Min Act: -0.1699
Data Index: 2013221 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1079. Min Range: -2.1079
Max Act: 1.9902. Min Act: -0.1700
Data Index: 2718803 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1079. Min Range: -2.1079
Max Act: 1.9902. Min Act: -0.1700
Data Index: 4376468 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1079. Min Range: -2.1079
Max Act: 1.9732. Min Act: -0.1700
Data Index: 1656054 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1079. Min Range: -2.1079
Max Act: 1.9732. Min Act: -0.1700
Data Index: 7729719 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1079. Min Range: -2.1079
Max Act: 1.9563. Min Act: -0.1700
Data Index: 8662824 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1079. Min Range: -2.1079
Max Act: 1.9563. Min Act: -0.1700
Data Index: 1245958 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1079. Min Range: -2.1079
Max Act: 1.9393. Min Act: -0.1700
Data Index: 6941326 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1079. Min Range: -2.1079
Max Act: 1.9393. Min Act: -0.1700
Data Index: 8808146 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1079. Min Range: -2.1079
Max Act: 1.9393. Min Act: -0.1700
Data Index: 5891391 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1079. Min Range: -2.1079
Max Act: 1.9223. Min Act: -0.1700
Data Index: 3688064 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1079. Min Range: -2.1079
Max Act: 1.9393. Min Act: -0.1700
Data Index: 3657956 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1079. Min Range: -2.1079
Max Act: 1.9223. Min Act: -0.1700
Data Index: 5772177 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1079. Min Range: -2.1079
Max Act: 1.9393. Min Act: -0.1700
Data Index: 7116991 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1079. Min Range: -2.1079
Max Act: 1.9223. Min Act: -0.1700
Data Index: 8808140 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1079. Min Range: -2.1079
Max Act: 1.9223. Min Act: -0.1700
Data Index: 8808141 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1079. Min Range: -2.1079
Max Act: 1.9223. Min Act: -0.1700
Data Index: 2049864 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1079. Min Range: -2.1079
Max Act: 1.9053. Min Act: -0.1698
Data Index: 3701761 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1079. Min Range: -2.1079
Max Act: 1.9223. Min Act: -0.1700
Data Index: 2457597 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #19