Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5328 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2593. Min Range: -6.2593
Max Act: 6.2593. Min Act: -0.1700
Data Index: 2240985 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2593. Min Range: -6.2593
Max Act: 6.1343. Min Act: -0.1700
Data Index: 4775026 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2593. Min Range: -6.2593
Max Act: 6.1030. Min Act: -0.1700
Data Index: 4430435 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2593. Min Range: -6.2593
Max Act: 6.1030. Min Act: -0.1700
Data Index: 5191798 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2593. Min Range: -6.2593
Max Act: 6.1030. Min Act: -0.1700
Data Index: 7663645 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2593. Min Range: -6.2593
Max Act: 6.1030. Min Act: -0.1700
Data Index: 460504 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2593. Min Range: -6.2593
Max Act: 6.0405. Min Act: -0.1700
Data Index: 8600829 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2593. Min Range: -6.2593
Max Act: 6.0405. Min Act: -0.1700
Data Index: 6824309 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2593. Min Range: -6.2593
Max Act: 5.9780. Min Act: -0.1700
Data Index: 8081721 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2593. Min Range: -6.2593
Max Act: 5.9780. Min Act: -0.1700
Data Index: 6916075 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2593. Min Range: -6.2593
Max Act: 5.9155. Min Act: -0.1700
Data Index: 6727431 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2593. Min Range: -6.2593
Max Act: 5.9468. Min Act: -0.1700
Data Index: 6765140 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2593. Min Range: -6.2593
Max Act: 5.9155. Min Act: -0.1700
Data Index: 5891782 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2593. Min Range: -6.2593
Max Act: 5.8843. Min Act: -0.1700
Data Index: 413505 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2593. Min Range: -6.2593
Max Act: 5.8843. Min Act: -0.1700
Data Index: 6191211 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2593. Min Range: -6.2593
Max Act: 5.8530. Min Act: -0.1700
Data Index: 4341066 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2593. Min Range: -6.2593
Max Act: 5.8843. Min Act: -0.1700
Data Index: 7732289 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2593. Min Range: -6.2593
Max Act: 5.8218. Min Act: -0.1700
Data Index: 5658525 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2593. Min Range: -6.2593
Max Act: 5.8218. Min Act: -0.1700
Data Index: 453447 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2593. Min Range: -6.2593
Max Act: 5.7905. Min Act: -0.1700
Data Index: 6951695 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #19