Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3934 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6954. Min Range: -4.6954
Max Act: 4.6954. Min Act: -0.1700
Data Index: 8678633 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6954. Min Range: -4.6954
Max Act: 4.6016. Min Act: -0.1700
Data Index: 487276 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6954. Min Range: -4.6954
Max Act: 4.4766. Min Act: -0.1700
Data Index: 5461497 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6954. Min Range: -4.6954
Max Act: 4.4766. Min Act: -0.1700
Data Index: 3841947 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6954. Min Range: -4.6954
Max Act: 4.4766. Min Act: -0.1700
Data Index: 4866686 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6954. Min Range: -4.6954
Max Act: 4.4454. Min Act: -0.1700
Data Index: 998077 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6954. Min Range: -4.6954
Max Act: 4.3829. Min Act: -0.1700
Data Index: 5863052 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6954. Min Range: -4.6954
Max Act: 4.3829. Min Act: -0.1700
Data Index: 6779185 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6954. Min Range: -4.6954
Max Act: 4.3829. Min Act: -0.1700
Data Index: 620105 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6954. Min Range: -4.6954
Max Act: 4.3516. Min Act: -0.1700
Data Index: 6744695 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6954. Min Range: -4.6954
Max Act: 4.3516. Min Act: -0.1700
Data Index: 6363044 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6954. Min Range: -4.6954
Max Act: 4.3204. Min Act: -0.1700
Data Index: 8328516 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6954. Min Range: -4.6954
Max Act: 4.3516. Min Act: -0.1700
Data Index: 8816628 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6954. Min Range: -4.6954
Max Act: 4.3516. Min Act: -0.1700
Data Index: 2067395 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6954. Min Range: -4.6954
Max Act: 4.3204. Min Act: -0.1700
Data Index: 1038543 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6954. Min Range: -4.6954
Max Act: 4.3204. Min Act: -0.1700
Data Index: 1774026 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6954. Min Range: -4.6954
Max Act: 4.3204. Min Act: -0.1700
Data Index: 6392564 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6954. Min Range: -4.6954
Max Act: 4.3204. Min Act: -0.1700
Data Index: 6484232 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6954. Min Range: -4.6954
Max Act: 4.3204. Min Act: -0.1700
Data Index: 2453643 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6954. Min Range: -4.6954
Max Act: 4.3204. Min Act: -0.1700
Data Index: 5717717 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #19