Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4945 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7896. Min Range: -5.7896
Max Act: 5.7896. Min Act: -0.1700
Data Index: 5008033 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7896. Min Range: -5.7896
Max Act: 5.7271. Min Act: -0.1700
Data Index: 6162501 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7896. Min Range: -5.7896
Max Act: 5.6334. Min Act: -0.1700
Data Index: 6162497 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7896. Min Range: -5.7896
Max Act: 5.4771. Min Act: -0.1700
Data Index: 3904011 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7896. Min Range: -5.7896
Max Act: 5.4146. Min Act: -0.1700
Data Index: 6369182 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7896. Min Range: -5.7896
Max Act: 5.4146. Min Act: -0.1700
Data Index: 1788428 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7896. Min Range: -5.7896
Max Act: 5.2896. Min Act: -0.1700
Data Index: 3982667 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7896. Min Range: -5.7896
Max Act: 5.2584. Min Act: -0.1700
Data Index: 3986694 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7896. Min Range: -5.7896
Max Act: 5.1646. Min Act: -0.1700
Data Index: 2889084 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7896. Min Range: -5.7896
Max Act: 5.1646. Min Act: -0.1700
Data Index: 8059810 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7896. Min Range: -5.7896
Max Act: 5.1021. Min Act: -0.1700
Data Index: 4220192 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7896. Min Range: -5.7896
Max Act: 5.1021. Min Act: -0.1700
Data Index: 7775719 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7896. Min Range: -5.7896
Max Act: 5.0709. Min Act: -0.1700
Data Index: 8301598 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7896. Min Range: -5.7896
Max Act: 5.0709. Min Act: -0.1700
Data Index: 1213581 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7896. Min Range: -5.7896
Max Act: 5.0709. Min Act: -0.1700
Data Index: 5008040 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7896. Min Range: -5.7896
Max Act: 5.0709. Min Act: -0.1700
Data Index: 5699803 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7896. Min Range: -5.7896
Max Act: 5.0709. Min Act: -0.1700
Data Index: 4724076 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7896. Min Range: -5.7896
Max Act: 5.0396. Min Act: -0.1700
Data Index: 3798146 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7896. Min Range: -5.7896
Max Act: 5.0396. Min Act: -0.1700
Data Index: 8614332 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7896. Min Range: -5.7896
Max Act: 5.0084. Min Act: -0.1700
Data Index: 1507077 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #19