Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3968 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4564. Min Range: -6.4564
Max Act: 6.4564. Min Act: -0.1700
Data Index: 5410833 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4564. Min Range: -6.4564
Max Act: 6.3001. Min Act: -0.1700
Data Index: 5473086 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4564. Min Range: -6.4564
Max Act: 6.1439. Min Act: -0.1700
Data Index: 6735652 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4564. Min Range: -6.4564
Max Act: 6.1126. Min Act: -0.1700
Data Index: 2476559 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4564. Min Range: -6.4564
Max Act: 6.0501. Min Act: -0.1700
Data Index: 1793326 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4564. Min Range: -6.4564
Max Act: 6.0189. Min Act: -0.1700
Data Index: 6669080 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4564. Min Range: -6.4564
Max Act: 5.9876. Min Act: -0.1700
Data Index: 129539 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4564. Min Range: -6.4564
Max Act: 5.9564. Min Act: -0.1700
Data Index: 6348 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4564. Min Range: -6.4564
Max Act: 5.9564. Min Act: -0.1700
Data Index: 4170000 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4564. Min Range: -6.4564
Max Act: 5.9564. Min Act: -0.1700
Data Index: 3640678 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4564. Min Range: -6.4564
Max Act: 5.9876. Min Act: -0.1700
Data Index: 3233841 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4564. Min Range: -6.4564
Max Act: 5.9564. Min Act: -0.1700
Data Index: 7389966 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4564. Min Range: -6.4564
Max Act: 5.9251. Min Act: -0.1700
Data Index: 3750404 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4564. Min Range: -6.4564
Max Act: 5.9251. Min Act: -0.1700
Data Index: 2167256 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4564. Min Range: -6.4564
Max Act: 5.8939. Min Act: -0.1700
Data Index: 8228464 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4564. Min Range: -6.4564
Max Act: 5.8939. Min Act: -0.1700
Data Index: 4111813 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4564. Min Range: -6.4564
Max Act: 5.8001. Min Act: -0.1700
Data Index: 3147769 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4564. Min Range: -6.4564
Max Act: 5.8314. Min Act: -0.1700
Data Index: 6472188 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4564. Min Range: -6.4564
Max Act: 5.8626. Min Act: -0.1700
Data Index: 5537762 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4564. Min Range: -6.4564
Max Act: 5.8001. Min Act: -0.1700
Data Index: 7642666 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #19