Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3086 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3842. Min Range: -7.3842
Max Act: 7.3842. Min Act: -0.1700
Data Index: 4296033 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3842. Min Range: -7.3842
Max Act: 7.2905. Min Act: -0.1700
Data Index: 4723818 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3842. Min Range: -7.3842
Max Act: 7.2905. Min Act: -0.1700
Data Index: 2469607 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3842. Min Range: -7.3842
Max Act: 7.2592. Min Act: -0.1700
Data Index: 3350810 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3842. Min Range: -7.3842
Max Act: 7.2280. Min Act: -0.1700
Data Index: 240213 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3842. Min Range: -7.3842
Max Act: 7.2280. Min Act: -0.1700
Data Index: 5043723 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3842. Min Range: -7.3842
Max Act: 7.1655. Min Act: -0.1700
Data Index: 272239 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3842. Min Range: -7.3842
Max Act: 7.1655. Min Act: -0.1700
Data Index: 1420924 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3842. Min Range: -7.3842
Max Act: 7.1655. Min Act: -0.1700
Data Index: 2632156 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3842. Min Range: -7.3842
Max Act: 7.1342. Min Act: -0.1700
Data Index: 1879271 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3842. Min Range: -7.3842
Max Act: 7.0717. Min Act: -0.1700
Data Index: 5615695 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3842. Min Range: -7.3842
Max Act: 7.0405. Min Act: -0.1700
Data Index: 8813332 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3842. Min Range: -7.3842
Max Act: 7.0717. Min Act: -0.1700
Data Index: 6149486 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3842. Min Range: -7.3842
Max Act: 7.0092. Min Act: -0.1700
Data Index: 8813330 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3842. Min Range: -7.3842
Max Act: 6.9780. Min Act: -0.1700
Data Index: 7291086 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3842. Min Range: -7.3842
Max Act: 6.9467. Min Act: -0.1700
Data Index: 2940562 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3842. Min Range: -7.3842
Max Act: 6.9780. Min Act: -0.1700
Data Index: 8073610 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3842. Min Range: -7.3842
Max Act: 6.9467. Min Act: -0.1700
Data Index: 7828322 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3842. Min Range: -7.3842
Max Act: 6.9467. Min Act: -0.1700
Data Index: 6077183 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3842. Min Range: -7.3842
Max Act: 6.9155. Min Act: -0.1700
Data Index: 5211708 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #19