Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2885 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6090. Min Range: -7.6090
Max Act: 7.6090. Min Act: -0.1700
Data Index: 5939223 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6090. Min Range: -7.6090
Max Act: 7.3278. Min Act: -0.1700
Data Index: 2594585 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6090. Min Range: -7.6090
Max Act: 7.2340. Min Act: -0.1700
Data Index: 7196351 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6090. Min Range: -7.6090
Max Act: 7.2028. Min Act: -0.1700
Data Index: 236970 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6090. Min Range: -7.6090
Max Act: 7.1715. Min Act: -0.1700
Data Index: 699950 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6090. Min Range: -7.6090
Max Act: 7.1715. Min Act: -0.1700
Data Index: 4292843 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6090. Min Range: -7.6090
Max Act: 7.0778. Min Act: -0.1700
Data Index: 8154730 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6090. Min Range: -7.6090
Max Act: 7.0465. Min Act: -0.1700
Data Index: 4871943 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6090. Min Range: -7.6090
Max Act: 7.0153. Min Act: -0.1700
Data Index: 4359952 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6090. Min Range: -7.6090
Max Act: 7.0153. Min Act: -0.1700
Data Index: 6820054 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6090. Min Range: -7.6090
Max Act: 6.9528. Min Act: -0.1700
Data Index: 8095452 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6090. Min Range: -7.6090
Max Act: 6.9215. Min Act: -0.1700
Data Index: 2270009 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6090. Min Range: -7.6090
Max Act: 6.9215. Min Act: -0.1700
Data Index: 8815325 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6090. Min Range: -7.6090
Max Act: 6.8903. Min Act: -0.1700
Data Index: 6301581 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6090. Min Range: -7.6090
Max Act: 6.8590. Min Act: -0.1700
Data Index: 4590736 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6090. Min Range: -7.6090
Max Act: 6.8590. Min Act: -0.1700
Data Index: 846544 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6090. Min Range: -7.6090
Max Act: 6.8590. Min Act: -0.1700
Data Index: 8184202 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6090. Min Range: -7.6090
Max Act: 6.8590. Min Act: -0.1700
Data Index: 6609280 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6090. Min Range: -7.6090
Max Act: 6.7965. Min Act: -0.1700
Data Index: 5929754 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6090. Min Range: -7.6090
Max Act: 6.7965. Min Act: -0.1700
Data Index: 883088 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #19