Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 654 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2387. Min Range: -4.2387
Max Act: 4.2387. Min Act: -0.1700
Data Index: 6104036 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2387. Min Range: -4.2387
Max Act: 4.0512. Min Act: -0.1700
Data Index: 4731105 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2387. Min Range: -4.2387
Max Act: 4.0512. Min Act: -0.1700
Data Index: 2960564 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2387. Min Range: -4.2387
Max Act: 4.0512. Min Act: -0.1700
Data Index: 3698997 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2387. Min Range: -4.2387
Max Act: 4.0512. Min Act: -0.1700
Data Index: 5162640 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2387. Min Range: -4.2387
Max Act: 3.9887. Min Act: -0.1700
Data Index: 135325 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2387. Min Range: -4.2387
Max Act: 3.9574. Min Act: -0.1699
Data Index: 3568388 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2387. Min Range: -4.2387
Max Act: 3.9574. Min Act: -0.1700
Data Index: 21919 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2387. Min Range: -4.2387
Max Act: 3.9261. Min Act: -0.1700
Data Index: 5256630 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2387. Min Range: -4.2387
Max Act: 3.8636. Min Act: -0.1700
Data Index: 5399424 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2387. Min Range: -4.2387
Max Act: 3.8636. Min Act: -0.1700
Data Index: 5070566 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2387. Min Range: -4.2387
Max Act: 3.8636. Min Act: -0.1700
Data Index: 400407 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2387. Min Range: -4.2387
Max Act: 3.8636. Min Act: -0.1700
Data Index: 7929379 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2387. Min Range: -4.2387
Max Act: 3.8323. Min Act: -0.1700
Data Index: 2524541 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2387. Min Range: -4.2387
Max Act: 3.8323. Min Act: -0.1700
Data Index: 3645690 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2387. Min Range: -4.2387
Max Act: 3.8011. Min Act: -0.1700
Data Index: 5546343 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2387. Min Range: -4.2387
Max Act: 3.8011. Min Act: -0.1700
Data Index: 385976 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2387. Min Range: -4.2387
Max Act: 3.8011. Min Act: -0.1700
Data Index: 5189420 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2387. Min Range: -4.2387
Max Act: 3.8011. Min Act: -0.1700
Data Index: 7654298 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2387. Min Range: -4.2387
Max Act: 3.8011. Min Act: -0.1700
Data Index: 4149907 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #19