Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3735 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8138. Min Range: -6.8138
Max Act: 6.8138. Min Act: -0.1700
Data Index: 2825704 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8138. Min Range: -6.8138
Max Act: 6.7825. Min Act: -0.1700
Data Index: 7710529 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8138. Min Range: -6.8138
Max Act: 6.7513. Min Act: -0.1700
Data Index: 8473416 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8138. Min Range: -6.8138
Max Act: 6.7200. Min Act: -0.1700
Data Index: 5426724 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8138. Min Range: -6.8138
Max Act: 6.7200. Min Act: -0.1700
Data Index: 1100017 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8138. Min Range: -6.8138
Max Act: 6.6888. Min Act: -0.1700
Data Index: 8579537 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8138. Min Range: -6.8138
Max Act: 6.6575. Min Act: -0.1700
Data Index: 2788324 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8138. Min Range: -6.8138
Max Act: 6.6263. Min Act: -0.1700
Data Index: 4557179 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8138. Min Range: -6.8138
Max Act: 6.6263. Min Act: -0.1700
Data Index: 6918848 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8138. Min Range: -6.8138
Max Act: 6.6263. Min Act: -0.1700
Data Index: 5194409 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8138. Min Range: -6.8138
Max Act: 6.6263. Min Act: -0.1700
Data Index: 7645794 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8138. Min Range: -6.8138
Max Act: 6.5638. Min Act: -0.1700
Data Index: 8691481 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8138. Min Range: -6.8138
Max Act: 6.5638. Min Act: -0.1700
Data Index: 6154623 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8138. Min Range: -6.8138
Max Act: 6.5638. Min Act: -0.1700
Data Index: 1096295 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8138. Min Range: -6.8138
Max Act: 6.5325. Min Act: -0.1700
Data Index: 704674 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8138. Min Range: -6.8138
Max Act: 6.5325. Min Act: -0.1700
Data Index: 8721861 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8138. Min Range: -6.8138
Max Act: 6.5325. Min Act: -0.1700
Data Index: 8240721 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8138. Min Range: -6.8138
Max Act: 6.5013. Min Act: -0.1700
Data Index: 8530671 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8138. Min Range: -6.8138
Max Act: 6.5013. Min Act: -0.1700
Data Index: 3450094 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8138. Min Range: -6.8138
Max Act: 6.4700. Min Act: -0.1700
Data Index: 7637560 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19