Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3368 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7383. Min Range: -6.7383
Max Act: 6.7383. Min Act: -0.1700
Data Index: 7295046 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7383. Min Range: -6.7383
Max Act: 6.5821. Min Act: -0.1700
Data Index: 113359 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7383. Min Range: -6.7383
Max Act: 6.5196. Min Act: -0.1700
Data Index: 4602164 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7383. Min Range: -6.7383
Max Act: 6.5196. Min Act: -0.1700
Data Index: 8725670 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7383. Min Range: -6.7383
Max Act: 6.4571. Min Act: -0.1700
Data Index: 8327085 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7383. Min Range: -6.7383
Max Act: 6.4571. Min Act: -0.1700
Data Index: 230223 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7383. Min Range: -6.7383
Max Act: 6.4258. Min Act: -0.1700
Data Index: 1189758 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7383. Min Range: -6.7383
Max Act: 6.3946. Min Act: -0.1700
Data Index: 2192841 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7383. Min Range: -6.7383
Max Act: 6.3633. Min Act: -0.1700
Data Index: 7266498 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7383. Min Range: -6.7383
Max Act: 6.2696. Min Act: -0.1700
Data Index: 3500074 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7383. Min Range: -6.7383
Max Act: 6.2696. Min Act: -0.1700
Data Index: 8359070 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7383. Min Range: -6.7383
Max Act: 6.2383. Min Act: -0.1700
Data Index: 1075235 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7383. Min Range: -6.7383
Max Act: 6.2071. Min Act: -0.1700
Data Index: 2247102 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7383. Min Range: -6.7383
Max Act: 6.2071. Min Act: -0.1700
Data Index: 1057465 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7383. Min Range: -6.7383
Max Act: 6.1758. Min Act: -0.1700
Data Index: 2074518 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7383. Min Range: -6.7383
Max Act: 6.1758. Min Act: -0.1700
Data Index: 2164976 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7383. Min Range: -6.7383
Max Act: 6.1446. Min Act: -0.1700
Data Index: 2532854 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7383. Min Range: -6.7383
Max Act: 6.1758. Min Act: -0.1700
Data Index: 6921348 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7383. Min Range: -6.7383
Max Act: 6.1446. Min Act: -0.1700
Data Index: 7998469 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7383. Min Range: -6.7383
Max Act: 6.1446. Min Act: -0.1700
Data Index: 4811384 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #19