Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2019 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5323. Min Range: -6.5323
Max Act: 6.5323. Min Act: -0.1700
Data Index: 7587795 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5323. Min Range: -6.5323
Max Act: 6.4698. Min Act: -0.1700
Data Index: 4697625 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5323. Min Range: -6.5323
Max Act: 6.5011. Min Act: -0.1700
Data Index: 5030809 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5323. Min Range: -6.5323
Max Act: 6.4073. Min Act: -0.1700
Data Index: 15474 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5323. Min Range: -6.5323
Max Act: 6.4073. Min Act: -0.1700
Data Index: 5748302 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5323. Min Range: -6.5323
Max Act: 6.3761. Min Act: -0.1700
Data Index: 2677787 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5323. Min Range: -6.5323
Max Act: 6.3761. Min Act: -0.1700
Data Index: 2294750 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5323. Min Range: -6.5323
Max Act: 6.3448. Min Act: -0.1700
Data Index: 7390682 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5323. Min Range: -6.5323
Max Act: 6.3136. Min Act: -0.1700
Data Index: 7509683 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5323. Min Range: -6.5323
Max Act: 6.3448. Min Act: -0.1700
Data Index: 3549716 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5323. Min Range: -6.5323
Max Act: 6.3136. Min Act: -0.1700
Data Index: 8091492 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5323. Min Range: -6.5323
Max Act: 6.2823. Min Act: -0.1700
Data Index: 6417655 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5323. Min Range: -6.5323
Max Act: 6.2823. Min Act: -0.1700
Data Index: 6406603 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5323. Min Range: -6.5323
Max Act: 6.2823. Min Act: -0.1700
Data Index: 6301000 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5323. Min Range: -6.5323
Max Act: 6.2511. Min Act: -0.1700
Data Index: 4291393 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5323. Min Range: -6.5323
Max Act: 6.1886. Min Act: -0.1700
Data Index: 1223296 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5323. Min Range: -6.5323
Max Act: 6.1886. Min Act: -0.1700
Data Index: 4529285 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5323. Min Range: -6.5323
Max Act: 6.1886. Min Act: -0.1700
Data Index: 7920443 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5323. Min Range: -6.5323
Max Act: 6.1886. Min Act: -0.1700
Data Index: 7620938 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5323. Min Range: -6.5323
Max Act: 6.1886. Min Act: -0.1700
Data Index: 2825223 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #19