Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2976 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0196. Min Range: -8.0196
Max Act: 8.0196. Min Act: -0.1700
Data Index: 6140732 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0196. Min Range: -8.0196
Max Act: 7.8946. Min Act: -0.1700
Data Index: 5925029 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0196. Min Range: -8.0196
Max Act: 7.8946. Min Act: -0.1700
Data Index: 2346714 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0196. Min Range: -8.0196
Max Act: 7.8321. Min Act: -0.1700
Data Index: 8754954 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0196. Min Range: -8.0196
Max Act: 7.8008. Min Act: -0.1700
Data Index: 2293920 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0196. Min Range: -8.0196
Max Act: 7.8008. Min Act: -0.1700
Data Index: 1685843 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0196. Min Range: -8.0196
Max Act: 7.7383. Min Act: -0.1700
Data Index: 3481853 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0196. Min Range: -8.0196
Max Act: 7.7696. Min Act: -0.1700
Data Index: 3622877 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0196. Min Range: -8.0196
Max Act: 7.7696. Min Act: -0.1700
Data Index: 4453755 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0196. Min Range: -8.0196
Max Act: 7.7696. Min Act: -0.1700
Data Index: 8020680 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0196. Min Range: -8.0196
Max Act: 7.7696. Min Act: -0.1700
Data Index: 4038558 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0196. Min Range: -8.0196
Max Act: 7.7383. Min Act: -0.1700
Data Index: 1700064 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0196. Min Range: -8.0196
Max Act: 7.6758. Min Act: -0.1700
Data Index: 4876229 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0196. Min Range: -8.0196
Max Act: 7.6758. Min Act: -0.1700
Data Index: 3052511 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0196. Min Range: -8.0196
Max Act: 7.6446. Min Act: -0.1700
Data Index: 1603833 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0196. Min Range: -8.0196
Max Act: 7.6133. Min Act: -0.1700
Data Index: 1033516 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0196. Min Range: -8.0196
Max Act: 7.5821. Min Act: -0.1700
Data Index: 6117349 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0196. Min Range: -8.0196
Max Act: 7.5821. Min Act: -0.1700
Data Index: 2331820 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0196. Min Range: -8.0196
Max Act: 7.5508. Min Act: -0.1700
Data Index: 8754955 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0196. Min Range: -8.0196
Max Act: 7.5196. Min Act: -0.1700
Data Index: 4278104 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #19