Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4636 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7957. Min Range: -4.7957
Max Act: 4.7957. Min Act: -0.1700
Data Index: 836928 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7957. Min Range: -4.7957
Max Act: 4.5457. Min Act: -0.1700
Data Index: 3330350 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7957. Min Range: -4.7957
Max Act: 4.4207. Min Act: -0.1700
Data Index: 2672713 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7957. Min Range: -4.7957
Max Act: 4.3269. Min Act: -0.1700
Data Index: 7520143 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7957. Min Range: -4.7957
Max Act: 4.2957. Min Act: -0.1700
Data Index: 5628062 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7957. Min Range: -4.7957
Max Act: 4.2957. Min Act: -0.1700
Data Index: 6588480 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7957. Min Range: -4.7957
Max Act: 4.2957. Min Act: -0.1700
Data Index: 357587 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7957. Min Range: -4.7957
Max Act: 4.2644. Min Act: -0.1700
Data Index: 6974374 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7957. Min Range: -4.7957
Max Act: 4.2019. Min Act: -0.1700
Data Index: 3719086 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7957. Min Range: -4.7957
Max Act: 4.2332. Min Act: -0.1700
Data Index: 2327606 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7957. Min Range: -4.7957
Max Act: 4.2332. Min Act: -0.1700
Data Index: 5423584 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7957. Min Range: -4.7957
Max Act: 4.2332. Min Act: -0.1700
Data Index: 5423585 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7957. Min Range: -4.7957
Max Act: 4.2332. Min Act: -0.1700
Data Index: 35297 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7957. Min Range: -4.7957
Max Act: 4.2332. Min Act: -0.1700
Data Index: 8129365 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7957. Min Range: -4.7957
Max Act: 4.2019. Min Act: -0.1700
Data Index: 4791137 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7957. Min Range: -4.7957
Max Act: 4.2019. Min Act: -0.1700
Data Index: 1668259 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7957. Min Range: -4.7957
Max Act: 4.2019. Min Act: -0.1700
Data Index: 1443633 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7957. Min Range: -4.7957
Max Act: 4.1707. Min Act: -0.1700
Data Index: 679834 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7957. Min Range: -4.7957
Max Act: 4.1707. Min Act: -0.1700
Data Index: 4479510 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7957. Min Range: -4.7957
Max Act: 4.1394. Min Act: -0.1700
Data Index: 4385523 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #19