Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1026 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0351. Min Range: -6.0351
Max Act: 6.0351. Min Act: -0.1700
Data Index: 6326794 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0351. Min Range: -6.0351
Max Act: 6.0039. Min Act: -0.1700
Data Index: 5394683 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0351. Min Range: -6.0351
Max Act: 6.0039. Min Act: -0.1700
Data Index: 5396164 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0351. Min Range: -6.0351
Max Act: 5.9726. Min Act: -0.1700
Data Index: 8521883 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0351. Min Range: -6.0351
Max Act: 5.8789. Min Act: -0.1700
Data Index: 6558874 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0351. Min Range: -6.0351
Max Act: 5.8164. Min Act: -0.1700
Data Index: 3367073 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0351. Min Range: -6.0351
Max Act: 5.8164. Min Act: -0.1700
Data Index: 6798402 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0351. Min Range: -6.0351
Max Act: 5.8476. Min Act: -0.1700
Data Index: 3476383 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0351. Min Range: -6.0351
Max Act: 5.8164. Min Act: -0.1700
Data Index: 7606099 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0351. Min Range: -6.0351
Max Act: 5.7851. Min Act: -0.1700
Data Index: 1149473 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0351. Min Range: -6.0351
Max Act: 5.7851. Min Act: -0.1700
Data Index: 4776846 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0351. Min Range: -6.0351
Max Act: 5.7851. Min Act: -0.1700
Data Index: 7194307 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0351. Min Range: -6.0351
Max Act: 5.7226. Min Act: -0.1700
Data Index: 2361345 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0351. Min Range: -6.0351
Max Act: 5.7851. Min Act: -0.1700
Data Index: 5581104 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0351. Min Range: -6.0351
Max Act: 5.7539. Min Act: -0.1700
Data Index: 8792506 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0351. Min Range: -6.0351
Max Act: 5.7539. Min Act: -0.1700
Data Index: 5435689 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0351. Min Range: -6.0351
Max Act: 5.7226. Min Act: -0.1700
Data Index: 1853911 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0351. Min Range: -6.0351
Max Act: 5.7226. Min Act: -0.1700
Data Index: 6180284 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0351. Min Range: -6.0351
Max Act: 5.7539. Min Act: -0.1700
Data Index: 8316399 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0351. Min Range: -6.0351
Max Act: 5.7539. Min Act: -0.1700
Data Index: 345426 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #19