Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3023 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4495. Min Range: -6.4495
Max Act: 6.4495. Min Act: -0.1700
Data Index: 2446566 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4495. Min Range: -6.4495
Max Act: 6.1058. Min Act: -0.1700
Data Index: 6446052 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4495. Min Range: -6.4495
Max Act: 6.0433. Min Act: -0.1700
Data Index: 7943751 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4495. Min Range: -6.4495
Max Act: 6.0120. Min Act: -0.1700
Data Index: 6536713 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4495. Min Range: -6.4495
Max Act: 5.9808. Min Act: -0.1700
Data Index: 6589665 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4495. Min Range: -6.4495
Max Act: 5.9495. Min Act: -0.1700
Data Index: 4854637 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4495. Min Range: -6.4495
Max Act: 5.9808. Min Act: -0.1700
Data Index: 7677552 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4495. Min Range: -6.4495
Max Act: 5.9495. Min Act: -0.1700
Data Index: 676023 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4495. Min Range: -6.4495
Max Act: 5.9495. Min Act: -0.1700
Data Index: 885515 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4495. Min Range: -6.4495
Max Act: 5.9183. Min Act: -0.1700
Data Index: 1627971 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4495. Min Range: -6.4495
Max Act: 5.8558. Min Act: -0.1700
Data Index: 3170325 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4495. Min Range: -6.4495
Max Act: 5.9183. Min Act: -0.1700
Data Index: 7867875 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4495. Min Range: -6.4495
Max Act: 5.8870. Min Act: -0.1700
Data Index: 1049401 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4495. Min Range: -6.4495
Max Act: 5.8245. Min Act: -0.1700
Data Index: 4208046 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4495. Min Range: -6.4495
Max Act: 5.7933. Min Act: -0.1700
Data Index: 1627972 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4495. Min Range: -6.4495
Max Act: 5.7933. Min Act: -0.1700
Data Index: 1627975 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4495. Min Range: -6.4495
Max Act: 5.7620. Min Act: -0.1700
Data Index: 914445 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4495. Min Range: -6.4495
Max Act: 5.7933. Min Act: -0.1700
Data Index: 2136365 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4495. Min Range: -6.4495
Max Act: 5.7308. Min Act: -0.1700
Data Index: 6959171 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4495. Min Range: -6.4495
Max Act: 5.7308. Min Act: -0.1700
Data Index: 2485633 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #19