Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3108 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8338. Min Range: -9.8338
Max Act: 9.8338. Min Act: -0.1700
Data Index: 5836846 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8338. Min Range: -9.8338
Max Act: 9.1463. Min Act: -0.1700
Data Index: 5021237 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8338. Min Range: -9.8338
Max Act: 9.0213. Min Act: -0.1700
Data Index: 4073129 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8338. Min Range: -9.8338
Max Act: 8.9588. Min Act: -0.1700
Data Index: 3060186 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8338. Min Range: -9.8338
Max Act: 8.9588. Min Act: -0.1700
Data Index: 8071564 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8338. Min Range: -9.8338
Max Act: 8.8963. Min Act: -0.1700
Data Index: 2385320 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8338. Min Range: -9.8338
Max Act: 8.8963. Min Act: -0.1700
Data Index: 8575774 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8338. Min Range: -9.8338
Max Act: 8.8963. Min Act: -0.1700
Data Index: 1843021 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8338. Min Range: -9.8338
Max Act: 8.7713. Min Act: -0.1700
Data Index: 7934704 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8338. Min Range: -9.8338
Max Act: 8.7088. Min Act: -0.1700
Data Index: 6699266 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8338. Min Range: -9.8338
Max Act: 8.7713. Min Act: -0.1700
Data Index: 2513670 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8338. Min Range: -9.8338
Max Act: 8.7713. Min Act: -0.1700
Data Index: 7778147 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8338. Min Range: -9.8338
Max Act: 8.7088. Min Act: -0.1700
Data Index: 2169185 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8338. Min Range: -9.8338
Max Act: 8.7088. Min Act: -0.1700
Data Index: 4733027 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8338. Min Range: -9.8338
Max Act: 8.7088. Min Act: -0.1700
Data Index: 102390 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8338. Min Range: -9.8338
Max Act: 8.6463. Min Act: -0.1700
Data Index: 7893674 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8338. Min Range: -9.8338
Max Act: 8.6463. Min Act: -0.1700
Data Index: 4660265 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8338. Min Range: -9.8338
Max Act: 8.6463. Min Act: -0.1700
Data Index: 6757749 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8338. Min Range: -9.8338
Max Act: 8.5838. Min Act: -0.1700
Data Index: 8297461 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8338. Min Range: -9.8338
Max Act: 8.5838. Min Act: -0.1700
Data Index: 7032402 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #19