Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 36 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2466. Min Range: -8.2466
Max Act: 8.2466. Min Act: -0.1700
Data Index: 3434595 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2466. Min Range: -8.2466
Max Act: 8.0591. Min Act: -0.1700
Data Index: 1694951 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2466. Min Range: -8.2466
Max Act: 7.9341. Min Act: -0.1700
Data Index: 4534663 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2466. Min Range: -8.2466
Max Act: 7.8403. Min Act: -0.1700
Data Index: 3835534 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2466. Min Range: -8.2466
Max Act: 7.6528. Min Act: -0.1700
Data Index: 5924961 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2466. Min Range: -8.2466
Max Act: 7.6528. Min Act: -0.1700
Data Index: 8459537 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2466. Min Range: -8.2466
Max Act: 7.5903. Min Act: -0.1700
Data Index: 1175429 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2466. Min Range: -8.2466
Max Act: 7.6216. Min Act: -0.1700
Data Index: 1086231 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2466. Min Range: -8.2466
Max Act: 7.4966. Min Act: -0.1700
Data Index: 4769679 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2466. Min Range: -8.2466
Max Act: 7.4653. Min Act: -0.1700
Data Index: 6859544 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2466. Min Range: -8.2466
Max Act: 7.4653. Min Act: -0.1700
Data Index: 602436 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2466. Min Range: -8.2466
Max Act: 7.4341. Min Act: -0.1700
Data Index: 4910353 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2466. Min Range: -8.2466
Max Act: 7.4028. Min Act: -0.1700
Data Index: 6166920 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2466. Min Range: -8.2466
Max Act: 7.4028. Min Act: -0.1700
Data Index: 4595266 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2466. Min Range: -8.2466
Max Act: 7.3403. Min Act: -0.1700
Data Index: 7100896 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2466. Min Range: -8.2466
Max Act: 7.3716. Min Act: -0.1700
Data Index: 7427411 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2466. Min Range: -8.2466
Max Act: 7.3403. Min Act: -0.1700
Data Index: 6487051 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2466. Min Range: -8.2466
Max Act: 7.3091. Min Act: -0.1700
Data Index: 4168121 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2466. Min Range: -8.2466
Max Act: 7.3403. Min Act: -0.1700
Data Index: 6603903 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2466. Min Range: -8.2466
Max Act: 7.3716. Min Act: -0.1700
Data Index: 6128258 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #19