Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4399 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7310. Min Range: -8.7310
Max Act: 8.7310. Min Act: -0.1700
Data Index: 4405368 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7310. Min Range: -8.7310
Max Act: 8.4810. Min Act: -0.1700
Data Index: 3634759 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7310. Min Range: -8.7310
Max Act: 8.4810. Min Act: -0.1700
Data Index: 6495329 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7310. Min Range: -8.7310
Max Act: 8.4185. Min Act: -0.1700
Data Index: 4878403 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7310. Min Range: -8.7310
Max Act: 8.3560. Min Act: -0.1700
Data Index: 6438566 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7310. Min Range: -8.7310
Max Act: 8.2310. Min Act: -0.1700
Data Index: 8434065 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7310. Min Range: -8.7310
Max Act: 8.1685. Min Act: -0.1700
Data Index: 2330998 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7310. Min Range: -8.7310
Max Act: 8.1685. Min Act: -0.1700
Data Index: 4352636 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7310. Min Range: -8.7310
Max Act: 8.1060. Min Act: -0.1700
Data Index: 718500 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7310. Min Range: -8.7310
Max Act: 8.1060. Min Act: -0.1700
Data Index: 5352312 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7310. Min Range: -8.7310
Max Act: 8.0435. Min Act: -0.1700
Data Index: 5056269 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7310. Min Range: -8.7310
Max Act: 8.0435. Min Act: -0.1700
Data Index: 2130261 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7310. Min Range: -8.7310
Max Act: 8.0435. Min Act: -0.1700
Data Index: 8756456 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7310. Min Range: -8.7310
Max Act: 8.0435. Min Act: -0.1700
Data Index: 8390716 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7310. Min Range: -8.7310
Max Act: 8.0435. Min Act: -0.1700
Data Index: 1586566 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7310. Min Range: -8.7310
Max Act: 8.0435. Min Act: -0.1700
Data Index: 654585 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7310. Min Range: -8.7310
Max Act: 7.9810. Min Act: -0.1700
Data Index: 466306 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7310. Min Range: -8.7310
Max Act: 7.9810. Min Act: -0.1700
Data Index: 5907062 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7310. Min Range: -8.7310
Max Act: 7.9185. Min Act: -0.1700
Data Index: 3813394 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7310. Min Range: -8.7310
Max Act: 7.8560. Min Act: -0.1700
Data Index: 1431700 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #19