Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5843 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.5124. Min Range: -11.5124
Max Act: 11.5124. Min Act: -0.1700
Data Index: 2725791 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.5124. Min Range: -11.5124
Max Act: 10.8874. Min Act: -0.1700
Data Index: 7907427 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.5124. Min Range: -11.5124
Max Act: 10.8249. Min Act: -0.1700
Data Index: 2511761 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.5124. Min Range: -11.5124
Max Act: 10.7624. Min Act: -0.1700
Data Index: 2511760 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.5124. Min Range: -11.5124
Max Act: 10.6999. Min Act: -0.1700
Data Index: 499957 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.5124. Min Range: -11.5124
Max Act: 10.6999. Min Act: -0.1700
Data Index: 1069940 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.5124. Min Range: -11.5124
Max Act: 10.5749. Min Act: -0.1700
Data Index: 180847 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.5124. Min Range: -11.5124
Max Act: 10.5749. Min Act: -0.1700
Data Index: 6475004 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.5124. Min Range: -11.5124
Max Act: 10.5749. Min Act: -0.1700
Data Index: 2725795 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.5124. Min Range: -11.5124
Max Act: 10.5124. Min Act: -0.1700
Data Index: 3555694 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.5124. Min Range: -11.5124
Max Act: 10.5124. Min Act: -0.1700
Data Index: 4742942 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.5124. Min Range: -11.5124
Max Act: 10.5124. Min Act: -0.1700
Data Index: 5187359 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.5124. Min Range: -11.5124
Max Act: 10.3874. Min Act: -0.1700
Data Index: 1039503 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.5124. Min Range: -11.5124
Max Act: 10.4499. Min Act: -0.1700
Data Index: 3785349 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.5124. Min Range: -11.5124
Max Act: 10.3874. Min Act: -0.1700
Data Index: 5867356 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.5124. Min Range: -11.5124
Max Act: 10.3874. Min Act: -0.1700
Data Index: 2515796 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.5124. Min Range: -11.5124
Max Act: 10.3874. Min Act: -0.1700
Data Index: 8101281 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.5124. Min Range: -11.5124
Max Act: 10.4499. Min Act: -0.1700
Data Index: 2725790 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.5124. Min Range: -11.5124
Max Act: 10.3249. Min Act: -0.1700
Data Index: 5115876 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.5124. Min Range: -11.5124
Max Act: 10.3249. Min Act: -0.1700
Data Index: 8585938 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #19