Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 55 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5656. Min Range: -6.5656
Max Act: 6.5656. Min Act: -0.1700
Data Index: 414310 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5656. Min Range: -6.5656
Max Act: 6.1281. Min Act: -0.1700
Data Index: 8505472 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5656. Min Range: -6.5656
Max Act: 6.0343. Min Act: -0.1700
Data Index: 5309234 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5656. Min Range: -6.5656
Max Act: 6.0031. Min Act: -0.1700
Data Index: 1833451 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5656. Min Range: -6.5656
Max Act: 5.9406. Min Act: -0.1700
Data Index: 4983019 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5656. Min Range: -6.5656
Max Act: 5.9718. Min Act: -0.1700
Data Index: 8027004 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5656. Min Range: -6.5656
Max Act: 5.9093. Min Act: -0.1700
Data Index: 277887 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5656. Min Range: -6.5656
Max Act: 5.9093. Min Act: -0.1700
Data Index: 77188 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5656. Min Range: -6.5656
Max Act: 5.8468. Min Act: -0.1700
Data Index: 8623391 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5656. Min Range: -6.5656
Max Act: 5.8781. Min Act: -0.1700
Data Index: 4410273 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5656. Min Range: -6.5656
Max Act: 5.8781. Min Act: -0.1700
Data Index: 6456824 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5656. Min Range: -6.5656
Max Act: 5.8468. Min Act: -0.1700
Data Index: 3834558 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5656. Min Range: -6.5656
Max Act: 5.8468. Min Act: -0.1700
Data Index: 5489964 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5656. Min Range: -6.5656
Max Act: 5.8468. Min Act: -0.1700
Data Index: 2980629 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5656. Min Range: -6.5656
Max Act: 5.8156. Min Act: -0.1700
Data Index: 5974031 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5656. Min Range: -6.5656
Max Act: 5.8156. Min Act: -0.1700
Data Index: 6263613 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5656. Min Range: -6.5656
Max Act: 5.8156. Min Act: -0.1700
Data Index: 2753827 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5656. Min Range: -6.5656
Max Act: 5.7843. Min Act: -0.1700
Data Index: 112069 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5656. Min Range: -6.5656
Max Act: 5.7531. Min Act: -0.1700
Data Index: 5941529 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5656. Min Range: -6.5656
Max Act: 5.7531. Min Act: -0.1700
Data Index: 3189003 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #19