Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 583 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1818. Min Range: -4.1818
Max Act: 4.1818. Min Act: -0.1700
Data Index: 7403029 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1818. Min Range: -4.1818
Max Act: 4.1506. Min Act: -0.1700
Data Index: 4208279 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1818. Min Range: -4.1818
Max Act: 4.1193. Min Act: -0.1700
Data Index: 3828072 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1818. Min Range: -4.1818
Max Act: 4.0256. Min Act: -0.1700
Data Index: 5193657 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1818. Min Range: -4.1818
Max Act: 3.9318. Min Act: -0.1700
Data Index: 2457423 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1818. Min Range: -4.1818
Max Act: 3.9630. Min Act: -0.1700
Data Index: 168739 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1818. Min Range: -4.1818
Max Act: 3.9630. Min Act: -0.1700
Data Index: 6820431 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1818. Min Range: -4.1818
Max Act: 3.9318. Min Act: -0.1700
Data Index: 2842765 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1818. Min Range: -4.1818
Max Act: 3.9630. Min Act: -0.1700
Data Index: 4719983 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1818. Min Range: -4.1818
Max Act: 3.9318. Min Act: -0.1700
Data Index: 3590636 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1818. Min Range: -4.1818
Max Act: 3.9005. Min Act: -0.1700
Data Index: 5409685 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1818. Min Range: -4.1818
Max Act: 3.9005. Min Act: -0.1700
Data Index: 1019796 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1818. Min Range: -4.1818
Max Act: 3.8692. Min Act: -0.1700
Data Index: 2213011 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1818. Min Range: -4.1818
Max Act: 3.9005. Min Act: -0.1700
Data Index: 5004219 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1818. Min Range: -4.1818
Max Act: 3.9005. Min Act: -0.1700
Data Index: 6276164 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1818. Min Range: -4.1818
Max Act: 3.8692. Min Act: -0.1700
Data Index: 451653 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1818. Min Range: -4.1818
Max Act: 3.8692. Min Act: -0.1700
Data Index: 2723712 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1818. Min Range: -4.1818
Max Act: 3.8380. Min Act: -0.1700
Data Index: 944087 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1818. Min Range: -4.1818
Max Act: 3.8692. Min Act: -0.1700
Data Index: 8652029 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1818. Min Range: -4.1818
Max Act: 3.8692. Min Act: -0.1700
Data Index: 647346 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #19