Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1890 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1447. Min Range: -3.1447
Max Act: 3.1447. Min Act: -0.1700
Data Index: 4816506 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1447. Min Range: -3.1447
Max Act: 3.0974. Min Act: -0.1700
Data Index: 8272492 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1447. Min Range: -3.1447
Max Act: 3.0974. Min Act: -0.1700
Data Index: 6194572 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1447. Min Range: -3.1447
Max Act: 3.0974. Min Act: -0.1700
Data Index: 12244 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1447. Min Range: -3.1447
Max Act: 3.0817. Min Act: -0.1700
Data Index: 5727598 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1447. Min Range: -3.1447
Max Act: 3.0817. Min Act: -0.1700
Data Index: 58096 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1447. Min Range: -3.1447
Max Act: 3.0501. Min Act: -0.1700
Data Index: 4816510 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1447. Min Range: -3.1447
Max Act: 3.0659. Min Act: -0.1700
Data Index: 4816524 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1447. Min Range: -3.1447
Max Act: 3.0343. Min Act: -0.1700
Data Index: 7575376 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1447. Min Range: -3.1447
Max Act: 3.0501. Min Act: -0.1700
Data Index: 8103930 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1447. Min Range: -3.1447
Max Act: 3.0343. Min Act: -0.1700
Data Index: 6113315 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1447. Min Range: -3.1447
Max Act: 3.0501. Min Act: -0.1700
Data Index: 1471280 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1447. Min Range: -3.1447
Max Act: 3.0027. Min Act: -0.1700
Data Index: 2372163 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1447. Min Range: -3.1447
Max Act: 2.9711. Min Act: -0.1700
Data Index: 2159724 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1447. Min Range: -3.1447
Max Act: 2.9711. Min Act: -0.1700
Data Index: 8206124 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1447. Min Range: -3.1447
Max Act: 3.0027. Min Act: -0.1700
Data Index: 4816523 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1447. Min Range: -3.1447
Max Act: 2.9869. Min Act: -0.1700
Data Index: 4775705 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1447. Min Range: -3.1447
Max Act: 3.0027. Min Act: -0.1700
Data Index: 4994281 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1447. Min Range: -3.1447
Max Act: 2.9711. Min Act: -0.1700
Data Index: 212671 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1447. Min Range: -3.1447
Max Act: 2.9395. Min Act: -0.1700
Data Index: 8011274 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #19