Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2500 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9085. Min Range: -3.9085
Max Act: 3.9085. Min Act: -0.1700
Data Index: 6206974 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9085. Min Range: -3.9085
Max Act: 3.8147. Min Act: -0.1700
Data Index: 3057384 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9085. Min Range: -3.9085
Max Act: 3.8460. Min Act: -0.1700
Data Index: 2910375 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9085. Min Range: -3.9085
Max Act: 3.7365. Min Act: -0.1700
Data Index: 1500136 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9085. Min Range: -3.9085
Max Act: 3.7835. Min Act: -0.1700
Data Index: 7367072 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9085. Min Range: -3.9085
Max Act: 3.7522. Min Act: -0.1700
Data Index: 4738622 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9085. Min Range: -3.9085
Max Act: 3.7209. Min Act: -0.1700
Data Index: 4227558 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9085. Min Range: -3.9085
Max Act: 3.7053. Min Act: -0.1700
Data Index: 5671964 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9085. Min Range: -3.9085
Max Act: 3.7209. Min Act: -0.1700
Data Index: 6417507 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9085. Min Range: -3.9085
Max Act: 3.6896. Min Act: -0.1700
Data Index: 2064618 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9085. Min Range: -3.9085
Max Act: 3.6740. Min Act: -0.1700
Data Index: 8168047 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9085. Min Range: -3.9085
Max Act: 3.6583. Min Act: -0.1700
Data Index: 8047793 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9085. Min Range: -3.9085
Max Act: 3.6427. Min Act: -0.1700
Data Index: 8340514 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9085. Min Range: -3.9085
Max Act: 3.6427. Min Act: -0.1700
Data Index: 8168046 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9085. Min Range: -3.9085
Max Act: 3.6427. Min Act: -0.1700
Data Index: 7294847 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9085. Min Range: -3.9085
Max Act: 3.6427. Min Act: -0.1700
Data Index: 1664204 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9085. Min Range: -3.9085
Max Act: 3.6427. Min Act: -0.1700
Data Index: 3073507 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9085. Min Range: -3.9085
Max Act: 3.6114. Min Act: -0.1700
Data Index: 8538662 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9085. Min Range: -3.9085
Max Act: 3.6114. Min Act: -0.1700
Data Index: 3920893 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9085. Min Range: -3.9085
Max Act: 3.6114. Min Act: -0.1700
Data Index: 6506117 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #19