Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3207 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9121. Min Range: -5.9121
Max Act: 5.9121. Min Act: -0.1700
Data Index: 868623 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9121. Min Range: -5.9121
Max Act: 5.4121. Min Act: -0.1700
Data Index: 4216128 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9121. Min Range: -5.9121
Max Act: 5.3808. Min Act: -0.1700
Data Index: 5488066 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9121. Min Range: -5.9121
Max Act: 5.3183. Min Act: -0.1700
Data Index: 3471091 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9121. Min Range: -5.9121
Max Act: 5.3496. Min Act: -0.1700
Data Index: 4638285 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9121. Min Range: -5.9121
Max Act: 5.3183. Min Act: -0.1700
Data Index: 7845950 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9121. Min Range: -5.9121
Max Act: 5.2871. Min Act: -0.1700
Data Index: 8234427 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9121. Min Range: -5.9121
Max Act: 5.2246. Min Act: -0.1700
Data Index: 95829 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9121. Min Range: -5.9121
Max Act: 5.2246. Min Act: -0.1700
Data Index: 3426855 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9121. Min Range: -5.9121
Max Act: 5.2246. Min Act: -0.1700
Data Index: 1583064 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9121. Min Range: -5.9121
Max Act: 5.2246. Min Act: -0.1700
Data Index: 92918 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9121. Min Range: -5.9121
Max Act: 5.1933. Min Act: -0.1700
Data Index: 8257625 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9121. Min Range: -5.9121
Max Act: 5.1933. Min Act: -0.1700
Data Index: 6872231 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9121. Min Range: -5.9121
Max Act: 5.1933. Min Act: -0.1700
Data Index: 1361062 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9121. Min Range: -5.9121
Max Act: 5.1621. Min Act: -0.1700
Data Index: 6393417 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9121. Min Range: -5.9121
Max Act: 5.1621. Min Act: -0.1700
Data Index: 8064960 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9121. Min Range: -5.9121
Max Act: 5.1933. Min Act: -0.1700
Data Index: 2728546 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9121. Min Range: -5.9121
Max Act: 5.1621. Min Act: -0.1700
Data Index: 655427 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9121. Min Range: -5.9121
Max Act: 5.1621. Min Act: -0.1700
Data Index: 3587166 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9121. Min Range: -5.9121
Max Act: 5.1621. Min Act: -0.1700
Data Index: 3728278 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #19