Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5502 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9656. Min Range: -5.9656
Max Act: 5.9656. Min Act: -0.1700
Data Index: 5635901 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9656. Min Range: -5.9656
Max Act: 5.9344. Min Act: -0.1700
Data Index: 926146 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9656. Min Range: -5.9656
Max Act: 5.9031. Min Act: -0.1700
Data Index: 2321639 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9656. Min Range: -5.9656
Max Act: 5.8719. Min Act: -0.1700
Data Index: 5338562 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9656. Min Range: -5.9656
Max Act: 5.8406. Min Act: -0.1700
Data Index: 583626 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9656. Min Range: -5.9656
Max Act: 5.8406. Min Act: -0.1700
Data Index: 2900808 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9656. Min Range: -5.9656
Max Act: 5.8406. Min Act: -0.1700
Data Index: 275890 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9656. Min Range: -5.9656
Max Act: 5.8406. Min Act: -0.1700
Data Index: 300778 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9656. Min Range: -5.9656
Max Act: 5.8094. Min Act: -0.1700
Data Index: 8825891 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9656. Min Range: -5.9656
Max Act: 5.8094. Min Act: -0.1700
Data Index: 6440235 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9656. Min Range: -5.9656
Max Act: 5.7469. Min Act: -0.1700
Data Index: 8380559 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9656. Min Range: -5.9656
Max Act: 5.8094. Min Act: -0.1700
Data Index: 8686399 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9656. Min Range: -5.9656
Max Act: 5.7781. Min Act: -0.1700
Data Index: 1790949 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9656. Min Range: -5.9656
Max Act: 5.7469. Min Act: -0.1700
Data Index: 5558513 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9656. Min Range: -5.9656
Max Act: 5.7469. Min Act: -0.1700
Data Index: 596302 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9656. Min Range: -5.9656
Max Act: 5.7156. Min Act: -0.1700
Data Index: 6947795 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9656. Min Range: -5.9656
Max Act: 5.7156. Min Act: -0.1700
Data Index: 3236911 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9656. Min Range: -5.9656
Max Act: 5.6844. Min Act: -0.1700
Data Index: 4435067 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9656. Min Range: -5.9656
Max Act: 5.7156. Min Act: -0.1700
Data Index: 2053639 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9656. Min Range: -5.9656
Max Act: 5.7156. Min Act: -0.1700
Data Index: 5971500 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #19