Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4455 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4363. Min Range: -7.4363
Max Act: 7.4363. Min Act: -0.1700
Data Index: 5667673 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4363. Min Range: -7.4363
Max Act: 7.4363. Min Act: -0.1700
Data Index: 2475035 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4363. Min Range: -7.4363
Max Act: 7.4051. Min Act: -0.1700
Data Index: 2394527 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4363. Min Range: -7.4363
Max Act: 7.4051. Min Act: -0.1700
Data Index: 4453567 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4363. Min Range: -7.4363
Max Act: 7.3738. Min Act: -0.1700
Data Index: 749378 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4363. Min Range: -7.4363
Max Act: 7.3738. Min Act: -0.1700
Data Index: 8282248 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4363. Min Range: -7.4363
Max Act: 7.3426. Min Act: -0.1700
Data Index: 2504296 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4363. Min Range: -7.4363
Max Act: 7.3738. Min Act: -0.1700
Data Index: 7691155 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4363. Min Range: -7.4363
Max Act: 7.3113. Min Act: -0.1700
Data Index: 7416130 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4363. Min Range: -7.4363
Max Act: 7.0613. Min Act: -0.1700
Data Index: 1712392 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4363. Min Range: -7.4363
Max Act: 7.0301. Min Act: -0.1700
Data Index: 8046476 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4363. Min Range: -7.4363
Max Act: 6.9676. Min Act: -0.1700
Data Index: 3587971 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4363. Min Range: -7.4363
Max Act: 6.9363. Min Act: -0.1700
Data Index: 7853733 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4363. Min Range: -7.4363
Max Act: 6.9051. Min Act: -0.1700
Data Index: 689722 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4363. Min Range: -7.4363
Max Act: 6.8426. Min Act: -0.1700
Data Index: 3548441 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4363. Min Range: -7.4363
Max Act: 6.9363. Min Act: -0.1700
Data Index: 946252 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4363. Min Range: -7.4363
Max Act: 6.8426. Min Act: -0.1700
Data Index: 2318 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4363. Min Range: -7.4363
Max Act: 6.7801. Min Act: -0.1700
Data Index: 2305 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4363. Min Range: -7.4363
Max Act: 6.7488. Min Act: -0.1700
Data Index: 2308 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4363. Min Range: -7.4363
Max Act: 6.7176. Min Act: -0.1700
Data Index: 8703208 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19