Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2766 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0893. Min Range: -9.0893
Max Act: 9.0893. Min Act: -0.1700
Data Index: 944719 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0893. Min Range: -9.0893
Max Act: 9.0893. Min Act: -0.1700
Data Index: 8827309 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0893. Min Range: -9.0893
Max Act: 8.8393. Min Act: -0.1700
Data Index: 668295 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0893. Min Range: -9.0893
Max Act: 8.7143. Min Act: -0.1700
Data Index: 5098160 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0893. Min Range: -9.0893
Max Act: 8.5893. Min Act: -0.1700
Data Index: 258802 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0893. Min Range: -9.0893
Max Act: 8.4643. Min Act: -0.1700
Data Index: 3162149 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0893. Min Range: -9.0893
Max Act: 8.4643. Min Act: -0.1700
Data Index: 8584430 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0893. Min Range: -9.0893
Max Act: 8.4643. Min Act: -0.1700
Data Index: 5137577 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0893. Min Range: -9.0893
Max Act: 8.4643. Min Act: -0.1700
Data Index: 5662968 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0893. Min Range: -9.0893
Max Act: 8.4643. Min Act: -0.1700
Data Index: 6878483 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0893. Min Range: -9.0893
Max Act: 8.4018. Min Act: -0.1700
Data Index: 5448957 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0893. Min Range: -9.0893
Max Act: 8.4018. Min Act: -0.1700
Data Index: 907500 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0893. Min Range: -9.0893
Max Act: 8.3393. Min Act: -0.1700
Data Index: 619870 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0893. Min Range: -9.0893
Max Act: 8.3393. Min Act: -0.1700
Data Index: 7011055 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0893. Min Range: -9.0893
Max Act: 8.3393. Min Act: -0.1700
Data Index: 8828205 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0893. Min Range: -9.0893
Max Act: 8.3393. Min Act: -0.1700
Data Index: 1306000 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0893. Min Range: -9.0893
Max Act: 8.3393. Min Act: -0.1700
Data Index: 7856169 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0893. Min Range: -9.0893
Max Act: 8.2768. Min Act: -0.1700
Data Index: 5742565 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0893. Min Range: -9.0893
Max Act: 8.2768. Min Act: -0.1700
Data Index: 7635878 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0893. Min Range: -9.0893
Max Act: 8.2768. Min Act: -0.1700
Data Index: 3757866 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #19