Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3769 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2300. Min Range: -7.2300
Max Act: 7.2300. Min Act: -0.1700
Data Index: 6391255 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2300. Min Range: -7.2300
Max Act: 7.1050. Min Act: -0.1700
Data Index: 7576396 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2300. Min Range: -7.2300
Max Act: 7.0738. Min Act: -0.1700
Data Index: 361909 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2300. Min Range: -7.2300
Max Act: 7.0425. Min Act: -0.1700
Data Index: 671539 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2300. Min Range: -7.2300
Max Act: 6.9800. Min Act: -0.1700
Data Index: 6073442 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2300. Min Range: -7.2300
Max Act: 6.9488. Min Act: -0.1700
Data Index: 4796080 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2300. Min Range: -7.2300
Max Act: 6.9175. Min Act: -0.1700
Data Index: 4299794 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2300. Min Range: -7.2300
Max Act: 6.9175. Min Act: -0.1700
Data Index: 1148980 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2300. Min Range: -7.2300
Max Act: 6.8863. Min Act: -0.1700
Data Index: 7948042 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2300. Min Range: -7.2300
Max Act: 6.8550. Min Act: -0.1700
Data Index: 7660872 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2300. Min Range: -7.2300
Max Act: 6.8550. Min Act: -0.1700
Data Index: 8754343 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2300. Min Range: -7.2300
Max Act: 6.8550. Min Act: -0.1700
Data Index: 3689597 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2300. Min Range: -7.2300
Max Act: 6.8550. Min Act: -0.1700
Data Index: 6273049 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2300. Min Range: -7.2300
Max Act: 6.8238. Min Act: -0.1700
Data Index: 4328140 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2300. Min Range: -7.2300
Max Act: 6.8238. Min Act: -0.1700
Data Index: 8027637 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2300. Min Range: -7.2300
Max Act: 6.8238. Min Act: -0.1700
Data Index: 7093138 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2300. Min Range: -7.2300
Max Act: 6.7925. Min Act: -0.1700
Data Index: 3437621 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2300. Min Range: -7.2300
Max Act: 6.8238. Min Act: -0.1700
Data Index: 6876806 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2300. Min Range: -7.2300
Max Act: 6.8238. Min Act: -0.1700
Data Index: 7005593 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2300. Min Range: -7.2300
Max Act: 6.7925. Min Act: -0.1700
Data Index: 3653650 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #19