Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2474 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2688. Min Range: -7.2688
Max Act: 7.2688. Min Act: -0.1700
Data Index: 2366017 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2688. Min Range: -7.2688
Max Act: 7.2063. Min Act: -0.1700
Data Index: 7890066 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2688. Min Range: -7.2688
Max Act: 7.1750. Min Act: -0.1700
Data Index: 8696962 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2688. Min Range: -7.2688
Max Act: 7.1438. Min Act: -0.1700
Data Index: 6719965 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2688. Min Range: -7.2688
Max Act: 7.0188. Min Act: -0.1700
Data Index: 7066648 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2688. Min Range: -7.2688
Max Act: 6.9875. Min Act: -0.1700
Data Index: 5353045 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2688. Min Range: -7.2688
Max Act: 6.9250. Min Act: -0.1700
Data Index: 2629809 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2688. Min Range: -7.2688
Max Act: 6.9875. Min Act: -0.1700
Data Index: 5581438 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2688. Min Range: -7.2688
Max Act: 6.8938. Min Act: -0.1700
Data Index: 2015667 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2688. Min Range: -7.2688
Max Act: 6.9250. Min Act: -0.1700
Data Index: 1166621 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2688. Min Range: -7.2688
Max Act: 6.9250. Min Act: -0.1700
Data Index: 587640 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2688. Min Range: -7.2688
Max Act: 6.9250. Min Act: -0.1700
Data Index: 5356234 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2688. Min Range: -7.2688
Max Act: 6.9250. Min Act: -0.1700
Data Index: 8821277 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2688. Min Range: -7.2688
Max Act: 6.9250. Min Act: -0.1700
Data Index: 6869920 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2688. Min Range: -7.2688
Max Act: 6.8313. Min Act: -0.1700
Data Index: 4966630 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2688. Min Range: -7.2688
Max Act: 6.8313. Min Act: -0.1700
Data Index: 5881678 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2688. Min Range: -7.2688
Max Act: 6.8313. Min Act: -0.1700
Data Index: 8694185 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2688. Min Range: -7.2688
Max Act: 6.8313. Min Act: -0.1700
Data Index: 5271363 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2688. Min Range: -7.2688
Max Act: 6.7688. Min Act: -0.1700
Data Index: 5977592 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2688. Min Range: -7.2688
Max Act: 6.7688. Min Act: -0.1700
Data Index: 2960975 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #19