Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 495 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8417. Min Range: -3.8417
Max Act: 3.8417. Min Act: -0.1700
Data Index: 2629870 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8417. Min Range: -3.8417
Max Act: 3.7009. Min Act: -0.1700
Data Index: 3245552 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8417. Min Range: -3.8417
Max Act: 3.6853. Min Act: -0.1700
Data Index: 355647 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8417. Min Range: -3.8417
Max Act: 3.5444. Min Act: -0.1700
Data Index: 6133439 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8417. Min Range: -3.8417
Max Act: 3.5601. Min Act: -0.1700
Data Index: 549900 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8417. Min Range: -3.8417
Max Act: 3.4504. Min Act: -0.1700
Data Index: 4362953 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8417. Min Range: -3.8417
Max Act: 3.4348. Min Act: -0.1700
Data Index: 5227900 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8417. Min Range: -3.8417
Max Act: 3.4034. Min Act: -0.1700
Data Index: 8739036 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8417. Min Range: -3.8417
Max Act: 3.4034. Min Act: -0.1700
Data Index: 8011245 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8417. Min Range: -3.8417
Max Act: 3.3721. Min Act: -0.1700
Data Index: 1758642 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8417. Min Range: -3.8417
Max Act: 3.3721. Min Act: -0.1700
Data Index: 4484444 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8417. Min Range: -3.8417
Max Act: 3.3721. Min Act: -0.1700
Data Index: 7264656 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8417. Min Range: -3.8417
Max Act: 3.3407. Min Act: -0.1700
Data Index: 6170980 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8417. Min Range: -3.8417
Max Act: 3.3407. Min Act: -0.1700
Data Index: 3310034 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8417. Min Range: -3.8417
Max Act: 3.3564. Min Act: -0.1700
Data Index: 5376779 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8417. Min Range: -3.8417
Max Act: 3.3250. Min Act: -0.1700
Data Index: 8728359 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8417. Min Range: -3.8417
Max Act: 3.3250. Min Act: -0.1700
Data Index: 3719325 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8417. Min Range: -3.8417
Max Act: 3.2936. Min Act: -0.1700
Data Index: 4908490 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8417. Min Range: -3.8417
Max Act: 3.2622. Min Act: -0.1700
Data Index: 3180058 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8417. Min Range: -3.8417
Max Act: 3.3093. Min Act: -0.1700
Data Index: 501900 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #19