Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4463 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0803. Min Range: -9.0803
Max Act: 9.0803. Min Act: -0.1700
Data Index: 4206455 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0803. Min Range: -9.0803
Max Act: 9.0803. Min Act: -0.1700
Data Index: 706543 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0803. Min Range: -9.0803
Max Act: 8.8303. Min Act: -0.1700
Data Index: 7812951 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0803. Min Range: -9.0803
Max Act: 8.8303. Min Act: -0.1700
Data Index: 2948432 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0803. Min Range: -9.0803
Max Act: 8.6428. Min Act: -0.1700
Data Index: 8533127 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0803. Min Range: -9.0803
Max Act: 8.6428. Min Act: -0.1700
Data Index: 748204 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0803. Min Range: -9.0803
Max Act: 8.5178. Min Act: -0.1700
Data Index: 8584869 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0803. Min Range: -9.0803
Max Act: 8.5178. Min Act: -0.1700
Data Index: 1407746 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0803. Min Range: -9.0803
Max Act: 8.4553. Min Act: -0.1700
Data Index: 2596335 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0803. Min Range: -9.0803
Max Act: 8.3928. Min Act: -0.1700
Data Index: 80795 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0803. Min Range: -9.0803
Max Act: 8.3928. Min Act: -0.1700
Data Index: 3628309 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0803. Min Range: -9.0803
Max Act: 8.3928. Min Act: -0.1700
Data Index: 910452 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0803. Min Range: -9.0803
Max Act: 8.3303. Min Act: -0.1700
Data Index: 2360873 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0803. Min Range: -9.0803
Max Act: 8.2678. Min Act: -0.1700
Data Index: 5985794 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0803. Min Range: -9.0803
Max Act: 8.2678. Min Act: -0.1700
Data Index: 6573165 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0803. Min Range: -9.0803
Max Act: 8.2678. Min Act: -0.1700
Data Index: 5944396 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0803. Min Range: -9.0803
Max Act: 8.3303. Min Act: -0.1700
Data Index: 5633095 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0803. Min Range: -9.0803
Max Act: 8.2678. Min Act: -0.1700
Data Index: 3633859 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0803. Min Range: -9.0803
Max Act: 8.2053. Min Act: -0.1700
Data Index: 3402214 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0803. Min Range: -9.0803
Max Act: 8.2053. Min Act: -0.1700
Data Index: 4168627 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #19