Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3498 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.1527. Min Range: -2.1527
Max Act: 2.1527. Min Act: -0.1700
Data Index: 4408455 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1527. Min Range: -2.1527
Max Act: 0.6881. Min Act: -0.1671
Data Index: 8752176 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1527. Min Range: -2.1527
Max Act: 0.7208. Min Act: -0.1700
Data Index: 5218047 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1527. Min Range: -2.1527
Max Act: 0.6800. Min Act: -0.1700
Data Index: 5277539 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1527. Min Range: -2.1527
Max Act: 0.6638. Min Act: -0.1700
Data Index: 1236718 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1527. Min Range: -2.1527
Max Act: 0.6719. Min Act: -0.1700
Data Index: 4993231 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1527. Min Range: -2.1527
Max Act: 0.6318. Min Act: -0.1698
Data Index: 4725512 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1527. Min Range: -2.1527
Max Act: 0.5844. Min Act: -0.1699
Data Index: 8808697 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1527. Min Range: -2.1527
Max Act: 0.5922. Min Act: -0.1700
Data Index: 3904550 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1527. Min Range: -2.1527
Max Act: 0.5766. Min Act: -0.1700
Data Index: 1857547 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1527. Min Range: -2.1527
Max Act: 0.5688. Min Act: -0.1691
Data Index: 2713191 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1527. Min Range: -2.1527
Max Act: 0.5380. Min Act: -0.1700
Data Index: 2131012 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1527. Min Range: -2.1527
Max Act: 0.5227. Min Act: -0.1700
Data Index: 1180093 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1527. Min Range: -2.1527
Max Act: 0.5227. Min Act: -0.1700
Data Index: 4400627 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1527. Min Range: -2.1527
Max Act: 0.5151. Min Act: -0.1700
Data Index: 1567439 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1527. Min Range: -2.1527
Max Act: 0.5380. Min Act: -0.1700
Data Index: 8676513 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1527. Min Range: -2.1527
Max Act: 0.5151. Min Act: -0.1696
Data Index: 703413 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1527. Min Range: -2.1527
Max Act: 0.5076. Min Act: -0.1700
Data Index: 5735575 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1527. Min Range: -2.1527
Max Act: 0.5151. Min Act: -0.1700
Data Index: 3543730 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1527. Min Range: -2.1527
Max Act: 0.4925. Min Act: -0.1700
Data Index: 4318040 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #19