Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 3049 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 7.7189. Min Range: -7.7189
Max Act: 7.7189. Min Act: -0.1700
Data Index: 8349214 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7189. Min Range: -7.7189
Max Act: 7.6564. Min Act: -0.1700
Data Index: 4464725 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7189. Min Range: -7.7189
Max Act: 7.4689. Min Act: -0.1700
Data Index: 5579877 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7189. Min Range: -7.7189
Max Act: 7.4689. Min Act: -0.1700
Data Index: 2613274 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7189. Min Range: -7.7189
Max Act: 7.4377. Min Act: -0.1700
Data Index: 3073211 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7189. Min Range: -7.7189
Max Act: 7.4064. Min Act: -0.1700
Data Index: 1159524 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7189. Min Range: -7.7189
Max Act: 7.3127. Min Act: -0.1700
Data Index: 1305918 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7189. Min Range: -7.7189
Max Act: 7.3127. Min Act: -0.1700
Data Index: 8312326 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7189. Min Range: -7.7189
Max Act: 7.2814. Min Act: -0.1700
Data Index: 5112659 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7189. Min Range: -7.7189
Max Act: 7.2814. Min Act: -0.1700
Data Index: 2240238 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7189. Min Range: -7.7189
Max Act: 7.2189. Min Act: -0.1700
Data Index: 7070402 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7189. Min Range: -7.7189
Max Act: 7.1252. Min Act: -0.1700
Data Index: 7869394 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7189. Min Range: -7.7189
Max Act: 7.1252. Min Act: -0.1700
Data Index: 6034898 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7189. Min Range: -7.7189
Max Act: 7.0627. Min Act: -0.1700
Data Index: 8197698 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7189. Min Range: -7.7189
Max Act: 7.0939. Min Act: -0.1700
Data Index: 6811436 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7189. Min Range: -7.7189
Max Act: 7.0627. Min Act: -0.1700
Data Index: 2446895 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7189. Min Range: -7.7189
Max Act: 7.0939. Min Act: -0.1700
Data Index: 4175703 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7189. Min Range: -7.7189
Max Act: 7.1252. Min Act: -0.1700
Data Index: 6509633 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7189. Min Range: -7.7189
Max Act: 6.8752. Min Act: -0.1700
Data Index: 1007301 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7189. Min Range: -7.7189
Max Act: 7.0627. Min Act: -0.1700
Data Index: 183164 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #19