Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1382 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6921. Min Range: -8.6921
Max Act: 8.6921. Min Act: -0.1700
Data Index: 1543716 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6921. Min Range: -8.6921
Max Act: 8.6296. Min Act: -0.1700
Data Index: 3460256 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6921. Min Range: -8.6921
Max Act: 8.4421. Min Act: -0.1700
Data Index: 5848703 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6921. Min Range: -8.6921
Max Act: 8.3171. Min Act: -0.1700
Data Index: 7783723 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6921. Min Range: -8.6921
Max Act: 8.1921. Min Act: -0.1700
Data Index: 7091925 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6921. Min Range: -8.6921
Max Act: 8.1921. Min Act: -0.1700
Data Index: 587480 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6921. Min Range: -8.6921
Max Act: 8.0671. Min Act: -0.1700
Data Index: 3033831 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6921. Min Range: -8.6921
Max Act: 7.9734. Min Act: -0.1700
Data Index: 6832810 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6921. Min Range: -8.6921
Max Act: 7.9421. Min Act: -0.1700
Data Index: 4943978 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6921. Min Range: -8.6921
Max Act: 7.8484. Min Act: -0.1700
Data Index: 3043723 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6921. Min Range: -8.6921
Max Act: 7.8796. Min Act: -0.1700
Data Index: 3687079 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6921. Min Range: -8.6921
Max Act: 7.8484. Min Act: -0.1700
Data Index: 4870529 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6921. Min Range: -8.6921
Max Act: 7.8171. Min Act: -0.1700
Data Index: 8719790 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6921. Min Range: -8.6921
Max Act: 7.7546. Min Act: -0.1700
Data Index: 7666728 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6921. Min Range: -8.6921
Max Act: 7.7234. Min Act: -0.1700
Data Index: 1271560 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6921. Min Range: -8.6921
Max Act: 7.7234. Min Act: -0.1700
Data Index: 8545069 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6921. Min Range: -8.6921
Max Act: 7.6921. Min Act: -0.1700
Data Index: 2623260 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6921. Min Range: -8.6921
Max Act: 7.6609. Min Act: -0.1700
Data Index: 6763862 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6921. Min Range: -8.6921
Max Act: 7.6609. Min Act: -0.1700
Data Index: 4686821 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6921. Min Range: -8.6921
Max Act: 7.5984. Min Act: -0.1700
Data Index: 999747 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #19