Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4102 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8831. Min Range: -6.8831
Max Act: 6.8831. Min Act: -0.1700
Data Index: 8528292 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8831. Min Range: -6.8831
Max Act: 6.8518. Min Act: -0.1700
Data Index: 317441 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8831. Min Range: -6.8831
Max Act: 6.7893. Min Act: -0.1700
Data Index: 117601 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8831. Min Range: -6.8831
Max Act: 6.7268. Min Act: -0.1700
Data Index: 368688 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8831. Min Range: -6.8831
Max Act: 6.6018. Min Act: -0.1700
Data Index: 8280195 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8831. Min Range: -6.8831
Max Act: 6.5706. Min Act: -0.1700
Data Index: 108753 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8831. Min Range: -6.8831
Max Act: 6.5393. Min Act: -0.1700
Data Index: 4231820 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8831. Min Range: -6.8831
Max Act: 6.5081. Min Act: -0.1700
Data Index: 4682816 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8831. Min Range: -6.8831
Max Act: 6.5081. Min Act: -0.1700
Data Index: 5932852 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8831. Min Range: -6.8831
Max Act: 6.4768. Min Act: -0.1700
Data Index: 6777981 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8831. Min Range: -6.8831
Max Act: 6.4768. Min Act: -0.1700
Data Index: 6517443 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8831. Min Range: -6.8831
Max Act: 6.3831. Min Act: -0.1700
Data Index: 1487846 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8831. Min Range: -6.8831
Max Act: 6.3831. Min Act: -0.1700
Data Index: 6660833 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8831. Min Range: -6.8831
Max Act: 6.3518. Min Act: -0.1700
Data Index: 3980576 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8831. Min Range: -6.8831
Max Act: 6.3206. Min Act: -0.1700
Data Index: 8486801 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8831. Min Range: -6.8831
Max Act: 6.3206. Min Act: -0.1700
Data Index: 2406155 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8831. Min Range: -6.8831
Max Act: 6.2893. Min Act: -0.1700
Data Index: 8497676 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8831. Min Range: -6.8831
Max Act: 6.2893. Min Act: -0.1700
Data Index: 4190870 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8831. Min Range: -6.8831
Max Act: 6.2581. Min Act: -0.1700
Data Index: 8087575 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8831. Min Range: -6.8831
Max Act: 6.2268. Min Act: -0.1700
Data Index: 7911631 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #19