Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4314 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6803. Min Range: -5.6803
Max Act: 5.6803. Min Act: -0.1700
Data Index: 8239515 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6803. Min Range: -5.6803
Max Act: 5.6178. Min Act: -0.1700
Data Index: 816205 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6803. Min Range: -5.6803
Max Act: 5.6178. Min Act: -0.1700
Data Index: 1089393 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6803. Min Range: -5.6803
Max Act: 5.5865. Min Act: -0.1700
Data Index: 748583 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6803. Min Range: -5.6803
Max Act: 5.4615. Min Act: -0.1700
Data Index: 192625 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6803. Min Range: -5.6803
Max Act: 5.4615. Min Act: -0.1700
Data Index: 5973232 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6803. Min Range: -5.6803
Max Act: 5.4615. Min Act: -0.1700
Data Index: 7058316 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6803. Min Range: -5.6803
Max Act: 5.4615. Min Act: -0.1700
Data Index: 634631 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6803. Min Range: -5.6803
Max Act: 5.4303. Min Act: -0.1700
Data Index: 8241589 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6803. Min Range: -5.6803
Max Act: 5.3678. Min Act: -0.1700
Data Index: 5066015 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6803. Min Range: -5.6803
Max Act: 5.3678. Min Act: -0.1700
Data Index: 37497 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6803. Min Range: -5.6803
Max Act: 5.2428. Min Act: -0.1700
Data Index: 7899564 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6803. Min Range: -5.6803
Max Act: 5.2740. Min Act: -0.1700
Data Index: 1094282 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6803. Min Range: -5.6803
Max Act: 5.2428. Min Act: -0.1700
Data Index: 4518411 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6803. Min Range: -5.6803
Max Act: 5.2115. Min Act: -0.1700
Data Index: 2243134 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6803. Min Range: -5.6803
Max Act: 5.2115. Min Act: -0.1700
Data Index: 3073291 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6803. Min Range: -5.6803
Max Act: 5.2115. Min Act: -0.1700
Data Index: 8141785 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6803. Min Range: -5.6803
Max Act: 5.2115. Min Act: -0.1700
Data Index: 4544255 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6803. Min Range: -5.6803
Max Act: 5.2115. Min Act: -0.1700
Data Index: 2168178 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6803. Min Range: -5.6803
Max Act: 5.2115. Min Act: -0.1700
Data Index: 1626324 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19