Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 157 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.7536. Min Act: -0.1700
Data Index: 638329 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.7848. Min Act: -0.1700
Data Index: 5284504 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.8161. Min Act: -0.1700
Data Index: 5420105 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.7223. Min Act: -0.1700
Data Index: 3236827 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.6598. Min Act: -0.1700
Data Index: 2522336 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.6598. Min Act: -0.1700
Data Index: 3837633 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.6286. Min Act: -0.1700
Data Index: 4596423 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.5973. Min Act: -0.1700
Data Index: 1082038 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.5973. Min Act: -0.1700
Data Index: 6900381 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.5348. Min Act: -0.1700
Data Index: 2007757 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.5661. Min Act: -0.1700
Data Index: 4913617 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.5348. Min Act: -0.1700
Data Index: 6138190 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.4723. Min Act: -0.1700
Data Index: 8548914 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.5973. Min Act: -0.1700
Data Index: 2914960 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.5348. Min Act: -0.1700
Data Index: 660305 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.5661. Min Act: -0.1700
Data Index: 5034228 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.5973. Min Act: -0.1700
Data Index: 1130566 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.5348. Min Act: -0.1700
Data Index: 4096700 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.4723. Min Act: -0.1700
Data Index: 2898097 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.4723. Min Act: -0.1700
Data Index: 1340266 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #19