Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1229 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5053. Min Range: -7.5053
Max Act: 7.5053. Min Act: -0.1700
Data Index: 2849504 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5053. Min Range: -7.5053
Max Act: 7.5053. Min Act: -0.1700
Data Index: 602818 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5053. Min Range: -7.5053
Max Act: 7.4740. Min Act: -0.1700
Data Index: 8304540 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5053. Min Range: -7.5053
Max Act: 7.4740. Min Act: -0.1700
Data Index: 4619029 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5053. Min Range: -7.5053
Max Act: 7.3490. Min Act: -0.1700
Data Index: 1283625 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5053. Min Range: -7.5053
Max Act: 7.2865. Min Act: -0.1700
Data Index: 3245918 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5053. Min Range: -7.5053
Max Act: 7.2553. Min Act: -0.1700
Data Index: 7519397 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5053. Min Range: -7.5053
Max Act: 7.2865. Min Act: -0.1700
Data Index: 3236697 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5053. Min Range: -7.5053
Max Act: 7.1928. Min Act: -0.1700
Data Index: 6241551 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5053. Min Range: -7.5053
Max Act: 7.1928. Min Act: -0.1700
Data Index: 8718987 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5053. Min Range: -7.5053
Max Act: 7.1615. Min Act: -0.1700
Data Index: 1086950 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5053. Min Range: -7.5053
Max Act: 7.0990. Min Act: -0.1700
Data Index: 4814723 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5053. Min Range: -7.5053
Max Act: 7.0990. Min Act: -0.1700
Data Index: 4781105 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5053. Min Range: -7.5053
Max Act: 7.0990. Min Act: -0.1700
Data Index: 5787326 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5053. Min Range: -7.5053
Max Act: 7.0365. Min Act: -0.1700
Data Index: 2256340 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5053. Min Range: -7.5053
Max Act: 7.0678. Min Act: -0.1700
Data Index: 4660254 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5053. Min Range: -7.5053
Max Act: 7.0365. Min Act: -0.1700
Data Index: 3768017 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5053. Min Range: -7.5053
Max Act: 7.0365. Min Act: -0.1700
Data Index: 6945652 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5053. Min Range: -7.5053
Max Act: 7.0053. Min Act: -0.1700
Data Index: 2774148 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5053. Min Range: -7.5053
Max Act: 7.0053. Min Act: -0.1700
Data Index: 5954997 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #19