Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3958 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1278. Min Range: -3.1278
Max Act: 3.1278. Min Act: -0.1700
Data Index: 1303643 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1278. Min Range: -3.1278
Max Act: 2.9541. Min Act: -0.1700
Data Index: 8534527 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1278. Min Range: -3.1278
Max Act: 2.9541. Min Act: -0.1700
Data Index: 3658062 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1278. Min Range: -3.1278
Max Act: 2.9383. Min Act: -0.1700
Data Index: 7731748 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1278. Min Range: -3.1278
Max Act: 2.9383. Min Act: -0.1700
Data Index: 3594 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1278. Min Range: -3.1278
Max Act: 2.8749. Min Act: -0.1700
Data Index: 1011779 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1278. Min Range: -3.1278
Max Act: 2.8749. Min Act: -0.1700
Data Index: 5410175 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1278. Min Range: -3.1278
Max Act: 2.8431. Min Act: -0.1700
Data Index: 4992229 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1278. Min Range: -3.1278
Max Act: 2.8431. Min Act: -0.1700
Data Index: 554335 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1278. Min Range: -3.1278
Max Act: 2.8431. Min Act: -0.1700
Data Index: 4901838 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1278. Min Range: -3.1278
Max Act: 2.8590. Min Act: -0.1700
Data Index: 6069819 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1278. Min Range: -3.1278
Max Act: 2.8590. Min Act: -0.1700
Data Index: 2956963 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1278. Min Range: -3.1278
Max Act: 2.8590. Min Act: -0.1700
Data Index: 5622791 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1278. Min Range: -3.1278
Max Act: 2.8272. Min Act: -0.1700
Data Index: 5731239 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1278. Min Range: -3.1278
Max Act: 2.8113. Min Act: -0.1700
Data Index: 545063 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1278. Min Range: -3.1278
Max Act: 2.8272. Min Act: -0.1700
Data Index: 2265738 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1278. Min Range: -3.1278
Max Act: 2.8113. Min Act: -0.1700
Data Index: 4705633 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1278. Min Range: -3.1278
Max Act: 2.7954. Min Act: -0.1700
Data Index: 6295773 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1278. Min Range: -3.1278
Max Act: 2.8431. Min Act: -0.1700
Data Index: 7167432 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1278. Min Range: -3.1278
Max Act: 2.7954. Min Act: -0.1700
Data Index: 2316286 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #19