Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3583 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.3087. Min Range: -9.3087
Max Act: 9.3087. Min Act: -0.1700
Data Index: 5236282 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3087. Min Range: -9.3087
Max Act: 9.1837. Min Act: -0.1700
Data Index: 1317781 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3087. Min Range: -9.3087
Max Act: 8.9962. Min Act: -0.1700
Data Index: 5578716 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3087. Min Range: -9.3087
Max Act: 8.9337. Min Act: -0.1700
Data Index: 2585447 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3087. Min Range: -9.3087
Max Act: 8.9962. Min Act: -0.1700
Data Index: 8719638 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3087. Min Range: -9.3087
Max Act: 8.8087. Min Act: -0.1700
Data Index: 331627 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3087. Min Range: -9.3087
Max Act: 8.8712. Min Act: -0.1700
Data Index: 2607712 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3087. Min Range: -9.3087
Max Act: 8.8087. Min Act: -0.1700
Data Index: 8108420 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3087. Min Range: -9.3087
Max Act: 8.7462. Min Act: -0.1700
Data Index: 1222139 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3087. Min Range: -9.3087
Max Act: 8.7462. Min Act: -0.1700
Data Index: 8084212 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3087. Min Range: -9.3087
Max Act: 8.6212. Min Act: -0.1700
Data Index: 5894045 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3087. Min Range: -9.3087
Max Act: 8.6837. Min Act: -0.1700
Data Index: 7147523 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3087. Min Range: -9.3087
Max Act: 8.5587. Min Act: -0.1700
Data Index: 3476081 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3087. Min Range: -9.3087
Max Act: 8.6212. Min Act: -0.1700
Data Index: 4949604 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3087. Min Range: -9.3087
Max Act: 8.5587. Min Act: -0.1700
Data Index: 1716143 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3087. Min Range: -9.3087
Max Act: 8.6212. Min Act: -0.1700
Data Index: 7269521 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3087. Min Range: -9.3087
Max Act: 8.4962. Min Act: -0.1700
Data Index: 2649970 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3087. Min Range: -9.3087
Max Act: 8.5587. Min Act: -0.1700
Data Index: 7674036 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3087. Min Range: -9.3087
Max Act: 8.5587. Min Act: -0.1700
Data Index: 5062718 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3087. Min Range: -9.3087
Max Act: 8.5587. Min Act: -0.1700
Data Index: 6964529 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #19