Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3495 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1186. Min Range: -5.1186
Max Act: 5.1186. Min Act: -0.1700
Data Index: 5582713 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1186. Min Range: -5.1186
Max Act: 4.9623. Min Act: -0.1700
Data Index: 6698444 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1186. Min Range: -5.1186
Max Act: 4.9311. Min Act: -0.1700
Data Index: 8153965 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1186. Min Range: -5.1186
Max Act: 4.9311. Min Act: -0.1700
Data Index: 1377090 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1186. Min Range: -5.1186
Max Act: 4.8998. Min Act: -0.1700
Data Index: 1559025 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1186. Min Range: -5.1186
Max Act: 4.9311. Min Act: -0.1700
Data Index: 280348 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1186. Min Range: -5.1186
Max Act: 4.8686. Min Act: -0.1700
Data Index: 4368211 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1186. Min Range: -5.1186
Max Act: 4.8373. Min Act: -0.1700
Data Index: 1661076 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1186. Min Range: -5.1186
Max Act: 4.8686. Min Act: -0.1700
Data Index: 7057741 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1186. Min Range: -5.1186
Max Act: 4.8061. Min Act: -0.1700
Data Index: 8340297 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1186. Min Range: -5.1186
Max Act: 4.8373. Min Act: -0.1700
Data Index: 8531125 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1186. Min Range: -5.1186
Max Act: 4.8373. Min Act: -0.1700
Data Index: 970962 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1186. Min Range: -5.1186
Max Act: 4.8373. Min Act: -0.1700
Data Index: 2452095 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1186. Min Range: -5.1186
Max Act: 4.8061. Min Act: -0.1700
Data Index: 1110899 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1186. Min Range: -5.1186
Max Act: 4.8061. Min Act: -0.1700
Data Index: 2867329 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1186. Min Range: -5.1186
Max Act: 4.8061. Min Act: -0.1700
Data Index: 6046232 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1186. Min Range: -5.1186
Max Act: 4.7748. Min Act: -0.1700
Data Index: 8177800 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1186. Min Range: -5.1186
Max Act: 4.7748. Min Act: -0.1700
Data Index: 6412094 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1186. Min Range: -5.1186
Max Act: 4.7748. Min Act: -0.1700
Data Index: 1110900 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1186. Min Range: -5.1186
Max Act: 4.7748. Min Act: -0.1700
Data Index: 6578856 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #19