Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2467 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0332. Min Range: -7.0332
Max Act: 7.0332. Min Act: -0.1700
Data Index: 7630501 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0332. Min Range: -7.0332
Max Act: 7.0332. Min Act: -0.1700
Data Index: 7630499 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0332. Min Range: -7.0332
Max Act: 7.0020. Min Act: -0.1700
Data Index: 396427 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0332. Min Range: -7.0332
Max Act: 6.9395. Min Act: -0.1700
Data Index: 6558533 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0332. Min Range: -7.0332
Max Act: 6.9707. Min Act: -0.1700
Data Index: 3799171 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0332. Min Range: -7.0332
Max Act: 7.0020. Min Act: -0.1700
Data Index: 396429 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0332. Min Range: -7.0332
Max Act: 6.9395. Min Act: -0.1700
Data Index: 6558535 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0332. Min Range: -7.0332
Max Act: 6.9082. Min Act: -0.1700
Data Index: 5883532 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0332. Min Range: -7.0332
Max Act: 6.8145. Min Act: -0.1700
Data Index: 6966241 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0332. Min Range: -7.0332
Max Act: 6.6895. Min Act: -0.1700
Data Index: 3782887 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0332. Min Range: -7.0332
Max Act: 6.6895. Min Act: -0.1700
Data Index: 8566536 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0332. Min Range: -7.0332
Max Act: 6.6895. Min Act: -0.1700
Data Index: 567431 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0332. Min Range: -7.0332
Max Act: 6.6582. Min Act: -0.1700
Data Index: 4561387 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0332. Min Range: -7.0332
Max Act: 6.6582. Min Act: -0.1700
Data Index: 8348706 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0332. Min Range: -7.0332
Max Act: 6.4707. Min Act: -0.1700
Data Index: 481857 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0332. Min Range: -7.0332
Max Act: 6.4707. Min Act: -0.1700
Data Index: 497616 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0332. Min Range: -7.0332
Max Act: 6.5332. Min Act: -0.1700
Data Index: 5409263 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0332. Min Range: -7.0332
Max Act: 6.4707. Min Act: -0.1700
Data Index: 3863238 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0332. Min Range: -7.0332
Max Act: 6.5020. Min Act: -0.1700
Data Index: 5936561 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0332. Min Range: -7.0332
Max Act: 6.4707. Min Act: -0.1700
Data Index: 5958376 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #19