Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4461 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4133. Min Range: -6.4133
Max Act: 6.4133. Min Act: -0.1700
Data Index: 465097 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4133. Min Range: -6.4133
Max Act: 6.4133. Min Act: -0.1700
Data Index: 8496470 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4133. Min Range: -6.4133
Max Act: 6.3820. Min Act: -0.1700
Data Index: 8675736 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4133. Min Range: -6.4133
Max Act: 6.3820. Min Act: -0.1700
Data Index: 81869 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4133. Min Range: -6.4133
Max Act: 6.3195. Min Act: -0.1700
Data Index: 7771849 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4133. Min Range: -6.4133
Max Act: 6.2883. Min Act: -0.1700
Data Index: 7567656 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4133. Min Range: -6.4133
Max Act: 6.2883. Min Act: -0.1700
Data Index: 1970978 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4133. Min Range: -6.4133
Max Act: 6.2883. Min Act: -0.1700
Data Index: 3742048 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4133. Min Range: -6.4133
Max Act: 6.2570. Min Act: -0.1700
Data Index: 3927400 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4133. Min Range: -6.4133
Max Act: 6.2570. Min Act: -0.1700
Data Index: 3281224 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4133. Min Range: -6.4133
Max Act: 6.2570. Min Act: -0.1700
Data Index: 1526606 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4133. Min Range: -6.4133
Max Act: 6.2258. Min Act: -0.1700
Data Index: 1003003 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4133. Min Range: -6.4133
Max Act: 6.2258. Min Act: -0.1700
Data Index: 8282030 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4133. Min Range: -6.4133
Max Act: 6.1945. Min Act: -0.1700
Data Index: 5052032 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4133. Min Range: -6.4133
Max Act: 6.1945. Min Act: -0.1700
Data Index: 732316 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4133. Min Range: -6.4133
Max Act: 6.1945. Min Act: -0.1700
Data Index: 7383351 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4133. Min Range: -6.4133
Max Act: 6.1945. Min Act: -0.1700
Data Index: 3063457 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4133. Min Range: -6.4133
Max Act: 6.1945. Min Act: -0.1700
Data Index: 2040599 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4133. Min Range: -6.4133
Max Act: 6.1633. Min Act: -0.1700
Data Index: 8102675 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4133. Min Range: -6.4133
Max Act: 6.1320. Min Act: -0.1700
Data Index: 2301925 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #19