Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 42 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8351. Min Range: -5.8351
Max Act: 5.8351. Min Act: -0.1700
Data Index: 152958 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8351. Min Range: -5.8351
Max Act: 5.7726. Min Act: -0.1700
Data Index: 538463 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8351. Min Range: -5.8351
Max Act: 5.6788. Min Act: -0.1700
Data Index: 7885228 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8351. Min Range: -5.8351
Max Act: 5.6788. Min Act: -0.1700
Data Index: 5555114 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8351. Min Range: -5.8351
Max Act: 5.6476. Min Act: -0.1700
Data Index: 2868707 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8351. Min Range: -5.8351
Max Act: 5.6163. Min Act: -0.1700
Data Index: 2986313 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8351. Min Range: -5.8351
Max Act: 5.6163. Min Act: -0.1700
Data Index: 7147652 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8351. Min Range: -5.8351
Max Act: 5.5851. Min Act: -0.1700
Data Index: 7095980 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8351. Min Range: -5.8351
Max Act: 5.5851. Min Act: -0.1700
Data Index: 4293714 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8351. Min Range: -5.8351
Max Act: 5.5851. Min Act: -0.1700
Data Index: 4171671 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8351. Min Range: -5.8351
Max Act: 5.5538. Min Act: -0.1700
Data Index: 6864506 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8351. Min Range: -5.8351
Max Act: 5.5226. Min Act: -0.1700
Data Index: 3470815 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8351. Min Range: -5.8351
Max Act: 5.4601. Min Act: -0.1700
Data Index: 7372229 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8351. Min Range: -5.8351
Max Act: 5.4601. Min Act: -0.1700
Data Index: 869475 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8351. Min Range: -5.8351
Max Act: 5.4913. Min Act: -0.1700
Data Index: 4041167 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8351. Min Range: -5.8351
Max Act: 5.4913. Min Act: -0.1700
Data Index: 2654342 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8351. Min Range: -5.8351
Max Act: 5.4913. Min Act: -0.1700
Data Index: 6400426 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8351. Min Range: -5.8351
Max Act: 5.4913. Min Act: -0.1700
Data Index: 3957989 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8351. Min Range: -5.8351
Max Act: 5.4913. Min Act: -0.1700
Data Index: 738622 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8351. Min Range: -5.8351
Max Act: 5.4913. Min Act: -0.1700
Data Index: 186237 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #19