Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 391 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.7472. Min Range: -1.7472
Max Act: 1.7472. Min Act: -0.1700
Data Index: 583725 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7472. Min Range: -1.7472
Max Act: 1.7039. Min Act: -0.1700
Data Index: 6773516 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7472. Min Range: -1.7472
Max Act: 1.6779. Min Act: -0.1700
Data Index: 8731801 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7472. Min Range: -1.7472
Max Act: 1.6692. Min Act: -0.1700
Data Index: 7609635 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7472. Min Range: -1.7472
Max Act: 1.6518. Min Act: -0.1700
Data Index: 5668351 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7472. Min Range: -1.7472
Max Act: 1.6257. Min Act: -0.1700
Data Index: 4911648 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7472. Min Range: -1.7472
Max Act: 1.6257. Min Act: -0.1700
Data Index: 291275 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7472. Min Range: -1.7472
Max Act: 1.6169. Min Act: -0.1700
Data Index: 5306623 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7472. Min Range: -1.7472
Max Act: 1.6082. Min Act: -0.1700
Data Index: 6171032 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7472. Min Range: -1.7472
Max Act: 1.6082. Min Act: -0.1700
Data Index: 3840928 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7472. Min Range: -1.7472
Max Act: 1.6082. Min Act: -0.1700
Data Index: 6348181 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7472. Min Range: -1.7472
Max Act: 1.5995. Min Act: -0.1700
Data Index: 2853815 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7472. Min Range: -1.7472
Max Act: 1.6082. Min Act: -0.1700
Data Index: 3742159 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7472. Min Range: -1.7472
Max Act: 1.5995. Min Act: -0.1700
Data Index: 1372738 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7472. Min Range: -1.7472
Max Act: 1.5995. Min Act: -0.1700
Data Index: 8139474 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7472. Min Range: -1.7472
Max Act: 1.5908. Min Act: -0.1700
Data Index: 4606960 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7472. Min Range: -1.7472
Max Act: 1.5908. Min Act: -0.1700
Data Index: 6612515 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7472. Min Range: -1.7472
Max Act: 1.5820. Min Act: -0.1700
Data Index: 8394032 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7472. Min Range: -1.7472
Max Act: 1.5820. Min Act: -0.1700
Data Index: 2977450 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7472. Min Range: -1.7472
Max Act: 1.5733. Min Act: -0.1700
Data Index: 3089540 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #19