Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 30 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4258. Min Range: -6.4258
Max Act: 6.4258. Min Act: -0.1700
Data Index: 3653651 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4258. Min Range: -6.4258
Max Act: 6.2696. Min Act: -0.1700
Data Index: 5272725 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4258. Min Range: -6.4258
Max Act: 5.8008. Min Act: -0.1700
Data Index: 8490101 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4258. Min Range: -6.4258
Max Act: 5.7383. Min Act: -0.1700
Data Index: 1529297 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4258. Min Range: -6.4258
Max Act: 5.6758. Min Act: -0.1700
Data Index: 6967270 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4258. Min Range: -6.4258
Max Act: 5.6446. Min Act: -0.1700
Data Index: 899495 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4258. Min Range: -6.4258
Max Act: 5.6446. Min Act: -0.1700
Data Index: 1680282 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4258. Min Range: -6.4258
Max Act: 5.6133. Min Act: -0.1700
Data Index: 261261 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4258. Min Range: -6.4258
Max Act: 5.6133. Min Act: -0.1700
Data Index: 8800684 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4258. Min Range: -6.4258
Max Act: 5.6133. Min Act: -0.1700
Data Index: 2909271 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4258. Min Range: -6.4258
Max Act: 5.6133. Min Act: -0.1700
Data Index: 6449588 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4258. Min Range: -6.4258
Max Act: 5.6446. Min Act: -0.1700
Data Index: 6603338 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4258. Min Range: -6.4258
Max Act: 5.6133. Min Act: -0.1700
Data Index: 5534154 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4258. Min Range: -6.4258
Max Act: 5.5821. Min Act: -0.1700
Data Index: 1120976 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4258. Min Range: -6.4258
Max Act: 5.5821. Min Act: -0.1700
Data Index: 3374659 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4258. Min Range: -6.4258
Max Act: 5.5508. Min Act: -0.1700
Data Index: 7981803 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4258. Min Range: -6.4258
Max Act: 5.5508. Min Act: -0.1700
Data Index: 3867505 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4258. Min Range: -6.4258
Max Act: 5.5196. Min Act: -0.1700
Data Index: 3674752 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4258. Min Range: -6.4258
Max Act: 5.4883. Min Act: -0.1700
Data Index: 2884946 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4258. Min Range: -6.4258
Max Act: 5.4883. Min Act: -0.1700
Data Index: 4804362 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #19