Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3921 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8883. Min Range: -5.8883
Max Act: 5.8883. Min Act: -0.1700
Data Index: 160569 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8883. Min Range: -5.8883
Max Act: 5.6383. Min Act: -0.1700
Data Index: 2359497 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8883. Min Range: -5.8883
Max Act: 5.5446. Min Act: -0.1700
Data Index: 2865276 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8883. Min Range: -5.8883
Max Act: 5.5446. Min Act: -0.1700
Data Index: 4291324 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8883. Min Range: -5.8883
Max Act: 5.4821. Min Act: -0.1700
Data Index: 277779 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8883. Min Range: -5.8883
Max Act: 5.4821. Min Act: -0.1700
Data Index: 160570 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8883. Min Range: -5.8883
Max Act: 5.4821. Min Act: -0.1700
Data Index: 584481 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8883. Min Range: -5.8883
Max Act: 5.4196. Min Act: -0.1700
Data Index: 4996259 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8883. Min Range: -5.8883
Max Act: 5.4196. Min Act: -0.1700
Data Index: 8085892 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8883. Min Range: -5.8883
Max Act: 5.4508. Min Act: -0.1700
Data Index: 1273597 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8883. Min Range: -5.8883
Max Act: 5.3883. Min Act: -0.1700
Data Index: 4546322 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8883. Min Range: -5.8883
Max Act: 5.3571. Min Act: -0.1700
Data Index: 160572 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8883. Min Range: -5.8883
Max Act: 5.3571. Min Act: -0.1700
Data Index: 277781 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8883. Min Range: -5.8883
Max Act: 5.3571. Min Act: -0.1700
Data Index: 8776116 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8883. Min Range: -5.8883
Max Act: 5.2946. Min Act: -0.1700
Data Index: 871874 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8883. Min Range: -5.8883
Max Act: 5.3258. Min Act: -0.1700
Data Index: 825833 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8883. Min Range: -5.8883
Max Act: 5.2321. Min Act: -0.1700
Data Index: 8774140 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8883. Min Range: -5.8883
Max Act: 5.2321. Min Act: -0.1700
Data Index: 7779635 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8883. Min Range: -5.8883
Max Act: 5.2321. Min Act: -0.1700
Data Index: 277780 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8883. Min Range: -5.8883
Max Act: 5.2321. Min Act: -0.1700
Data Index: 50870 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #19