Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3517 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0094. Min Range: -10.0094
Max Act: 10.0094. Min Act: -0.1700
Data Index: 1162138 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0094. Min Range: -10.0094
Max Act: 9.2594. Min Act: -0.1700
Data Index: 4323164 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0094. Min Range: -10.0094
Max Act: 9.2594. Min Act: -0.1700
Data Index: 2969641 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0094. Min Range: -10.0094
Max Act: 9.2594. Min Act: -0.1700
Data Index: 4222281 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0094. Min Range: -10.0094
Max Act: 9.1969. Min Act: -0.1700
Data Index: 2060136 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0094. Min Range: -10.0094
Max Act: 9.1969. Min Act: -0.1700
Data Index: 7463147 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0094. Min Range: -10.0094
Max Act: 9.1969. Min Act: -0.1700
Data Index: 7751641 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0094. Min Range: -10.0094
Max Act: 9.1969. Min Act: -0.1700
Data Index: 4825917 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0094. Min Range: -10.0094
Max Act: 9.1344. Min Act: -0.1700
Data Index: 4232422 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0094. Min Range: -10.0094
Max Act: 9.1344. Min Act: -0.1700
Data Index: 6840871 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0094. Min Range: -10.0094
Max Act: 9.0094. Min Act: -0.1700
Data Index: 7057169 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0094. Min Range: -10.0094
Max Act: 9.0094. Min Act: -0.1700
Data Index: 7070843 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0094. Min Range: -10.0094
Max Act: 9.0094. Min Act: -0.1700
Data Index: 79405 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0094. Min Range: -10.0094
Max Act: 9.0094. Min Act: -0.1700
Data Index: 6546165 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0094. Min Range: -10.0094
Max Act: 9.0094. Min Act: -0.1700
Data Index: 668400 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0094. Min Range: -10.0094
Max Act: 9.0094. Min Act: -0.1700
Data Index: 3155451 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0094. Min Range: -10.0094
Max Act: 8.9469. Min Act: -0.1700
Data Index: 6199316 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0094. Min Range: -10.0094
Max Act: 9.0094. Min Act: -0.1700
Data Index: 8057376 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0094. Min Range: -10.0094
Max Act: 8.9469. Min Act: -0.1700
Data Index: 2389061 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0094. Min Range: -10.0094
Max Act: 8.8844. Min Act: -0.1700
Data Index: 7961917 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #19