Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3175 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5354. Min Range: -5.5354
Max Act: 5.5354. Min Act: -0.1700
Data Index: 7364669 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5354. Min Range: -5.5354
Max Act: 5.4417. Min Act: -0.1700
Data Index: 1272342 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5354. Min Range: -5.5354
Max Act: 5.3479. Min Act: -0.1700
Data Index: 4400852 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5354. Min Range: -5.5354
Max Act: 5.3479. Min Act: -0.1700
Data Index: 4922146 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5354. Min Range: -5.5354
Max Act: 5.3167. Min Act: -0.1700
Data Index: 5553169 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5354. Min Range: -5.5354
Max Act: 5.3167. Min Act: -0.1700
Data Index: 6343810 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5354. Min Range: -5.5354
Max Act: 5.2854. Min Act: -0.1700
Data Index: 4400853 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5354. Min Range: -5.5354
Max Act: 5.2542. Min Act: -0.1700
Data Index: 799288 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5354. Min Range: -5.5354
Max Act: 5.2542. Min Act: -0.1700
Data Index: 6724543 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5354. Min Range: -5.5354
Max Act: 5.2542. Min Act: -0.1700
Data Index: 5993683 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5354. Min Range: -5.5354
Max Act: 5.2229. Min Act: -0.1700
Data Index: 3320353 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5354. Min Range: -5.5354
Max Act: 5.2229. Min Act: -0.1700
Data Index: 3812232 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5354. Min Range: -5.5354
Max Act: 5.2229. Min Act: -0.1700
Data Index: 7578048 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5354. Min Range: -5.5354
Max Act: 5.2229. Min Act: -0.1700
Data Index: 6487722 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5354. Min Range: -5.5354
Max Act: 5.2229. Min Act: -0.1700
Data Index: 1566095 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5354. Min Range: -5.5354
Max Act: 5.2229. Min Act: -0.1700
Data Index: 4400855 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5354. Min Range: -5.5354
Max Act: 5.1917. Min Act: -0.1700
Data Index: 4720440 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5354. Min Range: -5.5354
Max Act: 5.1917. Min Act: -0.1700
Data Index: 6314534 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5354. Min Range: -5.5354
Max Act: 5.1292. Min Act: -0.1700
Data Index: 806231 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5354. Min Range: -5.5354
Max Act: 5.1604. Min Act: -0.1700
Data Index: 5458452 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #19