Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2795 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7545. Min Range: -6.7545
Max Act: 6.7545. Min Act: -0.1700
Data Index: 864000 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7545. Min Range: -6.7545
Max Act: 6.6920. Min Act: -0.1700
Data Index: 4609720 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7545. Min Range: -6.7545
Max Act: 6.5983. Min Act: -0.1700
Data Index: 2104818 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7545. Min Range: -6.7545
Max Act: 6.5670. Min Act: -0.1700
Data Index: 4164986 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7545. Min Range: -6.7545
Max Act: 6.5358. Min Act: -0.1700
Data Index: 4349255 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7545. Min Range: -6.7545
Max Act: 6.5358. Min Act: -0.1700
Data Index: 1389732 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7545. Min Range: -6.7545
Max Act: 6.5045. Min Act: -0.1700
Data Index: 8308768 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7545. Min Range: -6.7545
Max Act: 6.5045. Min Act: -0.1700
Data Index: 4200051 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7545. Min Range: -6.7545
Max Act: 6.4733. Min Act: -0.1700
Data Index: 228358 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7545. Min Range: -6.7545
Max Act: 6.2858. Min Act: -0.1700
Data Index: 729714 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7545. Min Range: -6.7545
Max Act: 6.2545. Min Act: -0.1700
Data Index: 7895518 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7545. Min Range: -6.7545
Max Act: 6.1920. Min Act: -0.1700
Data Index: 4635374 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7545. Min Range: -6.7545
Max Act: 6.1920. Min Act: -0.1700
Data Index: 7262370 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7545. Min Range: -6.7545
Max Act: 6.1608. Min Act: -0.1700
Data Index: 810258 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7545. Min Range: -6.7545
Max Act: 6.1608. Min Act: -0.1700
Data Index: 4370217 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7545. Min Range: -6.7545
Max Act: 6.1608. Min Act: -0.1700
Data Index: 6967250 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7545. Min Range: -6.7545
Max Act: 6.1608. Min Act: -0.1700
Data Index: 1779025 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7545. Min Range: -6.7545
Max Act: 6.1295. Min Act: -0.1700
Data Index: 6647799 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7545. Min Range: -6.7545
Max Act: 6.1295. Min Act: -0.1700
Data Index: 2347004 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7545. Min Range: -6.7545
Max Act: 6.1295. Min Act: -0.1700
Data Index: 3377720 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #19