Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3958 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.4228. Min Range: -2.4228
Max Act: 2.4228. Min Act: -0.1700
Data Index: 8292654 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4228. Min Range: -2.4228
Max Act: 2.3575. Min Act: -0.1700
Data Index: 48163 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4228. Min Range: -2.4228
Max Act: 2.3411. Min Act: -0.1700
Data Index: 7393250 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4228. Min Range: -2.4228
Max Act: 2.3083. Min Act: -0.1700
Data Index: 903419 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4228. Min Range: -2.4228
Max Act: 2.2589. Min Act: -0.1700
Data Index: 3690668 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4228. Min Range: -2.4228
Max Act: 2.2754. Min Act: -0.1700
Data Index: 2050294 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4228. Min Range: -2.4228
Max Act: 2.2589. Min Act: -0.1700
Data Index: 8443314 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4228. Min Range: -2.4228
Max Act: 2.2423. Min Act: -0.1700
Data Index: 1151664 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4228. Min Range: -2.4228
Max Act: 2.2258. Min Act: -0.1700
Data Index: 5714570 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4228. Min Range: -2.4228
Max Act: 2.2258. Min Act: -0.1700
Data Index: 8429530 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4228. Min Range: -2.4228
Max Act: 2.2258. Min Act: -0.1700
Data Index: 494181 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4228. Min Range: -2.4228
Max Act: 2.2258. Min Act: -0.1700
Data Index: 6801393 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4228. Min Range: -2.4228
Max Act: 2.2258. Min Act: -0.1700
Data Index: 1667989 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4228. Min Range: -2.4228
Max Act: 2.2258. Min Act: -0.1700
Data Index: 6789769 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4228. Min Range: -2.4228
Max Act: 2.2258. Min Act: -0.1700
Data Index: 6604091 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4228. Min Range: -2.4228
Max Act: 2.2258. Min Act: -0.1700
Data Index: 2015459 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4228. Min Range: -2.4228
Max Act: 2.2092. Min Act: -0.1700
Data Index: 1428694 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4228. Min Range: -2.4228
Max Act: 2.1926. Min Act: -0.1700
Data Index: 468402 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4228. Min Range: -2.4228
Max Act: 2.2092. Min Act: -0.1700
Data Index: 6125126 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4228. Min Range: -2.4228
Max Act: 2.2092. Min Act: -0.1700
Data Index: 48164 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #19