Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4259 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9657. Min Range: -4.9657
Max Act: 4.9657. Min Act: -0.1700
Data Index: 5596326 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9657. Min Range: -4.9657
Max Act: 4.9657. Min Act: -0.1700
Data Index: 5726306 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9657. Min Range: -4.9657
Max Act: 4.9344. Min Act: -0.1700
Data Index: 4582369 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9657. Min Range: -4.9657
Max Act: 4.9344. Min Act: -0.1700
Data Index: 1779344 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9657. Min Range: -4.9657
Max Act: 4.8719. Min Act: -0.1700
Data Index: 3786826 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9657. Min Range: -4.9657
Max Act: 4.8407. Min Act: -0.1700
Data Index: 3095281 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9657. Min Range: -4.9657
Max Act: 4.8719. Min Act: -0.1700
Data Index: 2291853 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9657. Min Range: -4.9657
Max Act: 4.8094. Min Act: -0.1700
Data Index: 5058738 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9657. Min Range: -4.9657
Max Act: 4.8094. Min Act: -0.1700
Data Index: 797120 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9657. Min Range: -4.9657
Max Act: 4.8094. Min Act: -0.1699
Data Index: 7522405 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9657. Min Range: -4.9657
Max Act: 4.7782. Min Act: -0.1700
Data Index: 3095280 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9657. Min Range: -4.9657
Max Act: 4.7782. Min Act: -0.1700
Data Index: 3982420 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9657. Min Range: -4.9657
Max Act: 4.7782. Min Act: -0.1700
Data Index: 3918768 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9657. Min Range: -4.9657
Max Act: 4.7782. Min Act: -0.1700
Data Index: 5532085 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9657. Min Range: -4.9657
Max Act: 4.7782. Min Act: -0.1700
Data Index: 402321 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9657. Min Range: -4.9657
Max Act: 4.7782. Min Act: -0.1700
Data Index: 5532084 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9657. Min Range: -4.9657
Max Act: 4.7782. Min Act: -0.1700
Data Index: 4534280 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9657. Min Range: -4.9657
Max Act: 4.7782. Min Act: -0.1700
Data Index: 4170798 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9657. Min Range: -4.9657
Max Act: 4.7469. Min Act: -0.1700
Data Index: 5061296 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9657. Min Range: -4.9657
Max Act: 4.7469. Min Act: -0.1700
Data Index: 2106350 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #19