Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4771 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0742. Min Range: -7.0742
Max Act: 7.0742. Min Act: -0.1700
Data Index: 4722547 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0742. Min Range: -7.0742
Max Act: 6.8242. Min Act: -0.1700
Data Index: 1667037 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0742. Min Range: -7.0742
Max Act: 6.7617. Min Act: -0.1700
Data Index: 2123161 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0742. Min Range: -7.0742
Max Act: 6.7304. Min Act: -0.1700
Data Index: 2528028 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0742. Min Range: -7.0742
Max Act: 6.7304. Min Act: -0.1700
Data Index: 6031064 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0742. Min Range: -7.0742
Max Act: 6.7304. Min Act: -0.1700
Data Index: 829692 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0742. Min Range: -7.0742
Max Act: 6.6992. Min Act: -0.1700
Data Index: 6914624 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0742. Min Range: -7.0742
Max Act: 6.6367. Min Act: -0.1700
Data Index: 6360666 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0742. Min Range: -7.0742
Max Act: 6.5742. Min Act: -0.1700
Data Index: 4536895 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0742. Min Range: -7.0742
Max Act: 6.5429. Min Act: -0.1700
Data Index: 78032 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0742. Min Range: -7.0742
Max Act: 6.5117. Min Act: -0.1700
Data Index: 1310032 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0742. Min Range: -7.0742
Max Act: 6.5429. Min Act: -0.1700
Data Index: 3259360 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0742. Min Range: -7.0742
Max Act: 6.4804. Min Act: -0.1700
Data Index: 5165650 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0742. Min Range: -7.0742
Max Act: 6.4492. Min Act: -0.1700
Data Index: 2804507 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0742. Min Range: -7.0742
Max Act: 6.4492. Min Act: -0.1700
Data Index: 8555112 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0742. Min Range: -7.0742
Max Act: 6.4179. Min Act: -0.1700
Data Index: 1986162 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0742. Min Range: -7.0742
Max Act: 6.4492. Min Act: -0.1700
Data Index: 8525953 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0742. Min Range: -7.0742
Max Act: 6.4492. Min Act: -0.1700
Data Index: 6327325 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0742. Min Range: -7.0742
Max Act: 6.3867. Min Act: -0.1700
Data Index: 1072582 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0742. Min Range: -7.0742
Max Act: 6.4179. Min Act: -0.1700
Data Index: 8273705 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #19