Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2856 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7274. Min Range: -3.7274
Max Act: 3.7274. Min Act: -0.1700
Data Index: 4022292 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7274. Min Range: -3.7274
Max Act: 3.6022. Min Act: -0.1700
Data Index: 7128257 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7274. Min Range: -3.7274
Max Act: 3.6335. Min Act: -0.1700
Data Index: 4545697 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7274. Min Range: -3.7274
Max Act: 3.6022. Min Act: -0.1700
Data Index: 929873 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7274. Min Range: -3.7274
Max Act: 3.6022. Min Act: -0.1700
Data Index: 3598580 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7274. Min Range: -3.7274
Max Act: 3.6022. Min Act: -0.1700
Data Index: 7335993 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7274. Min Range: -3.7274
Max Act: 3.5866. Min Act: -0.1700
Data Index: 6509419 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7274. Min Range: -3.7274
Max Act: 3.5866. Min Act: -0.1700
Data Index: 7780450 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7274. Min Range: -3.7274
Max Act: 3.5709. Min Act: -0.1700
Data Index: 4319259 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7274. Min Range: -3.7274
Max Act: 3.5553. Min Act: -0.1700
Data Index: 3054340 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7274. Min Range: -3.7274
Max Act: 3.5709. Min Act: -0.1700
Data Index: 6605909 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7274. Min Range: -3.7274
Max Act: 3.5553. Min Act: -0.1700
Data Index: 5006119 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7274. Min Range: -3.7274
Max Act: 3.5396. Min Act: -0.1700
Data Index: 6358254 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7274. Min Range: -3.7274
Max Act: 3.5396. Min Act: -0.1700
Data Index: 790680 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7274. Min Range: -3.7274
Max Act: 3.5240. Min Act: -0.1700
Data Index: 3438195 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7274. Min Range: -3.7274
Max Act: 3.5240. Min Act: -0.1700
Data Index: 2866531 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7274. Min Range: -3.7274
Max Act: 3.5083. Min Act: -0.1700
Data Index: 5631159 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7274. Min Range: -3.7274
Max Act: 3.5240. Min Act: -0.1700
Data Index: 6003341 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7274. Min Range: -3.7274
Max Act: 3.4770. Min Act: -0.1700
Data Index: 5788025 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7274. Min Range: -3.7274
Max Act: 3.5083. Min Act: -0.1700
Data Index: 1662053 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #19