Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3128 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4326. Min Range: -7.4326
Max Act: 7.4326. Min Act: -0.1700
Data Index: 3218233 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4326. Min Range: -7.4326
Max Act: 7.4013. Min Act: -0.1700
Data Index: 8041642 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4326. Min Range: -7.4326
Max Act: 7.4013. Min Act: -0.1700
Data Index: 2812096 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4326. Min Range: -7.4326
Max Act: 7.2451. Min Act: -0.1700
Data Index: 5910137 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4326. Min Range: -7.4326
Max Act: 7.1826. Min Act: -0.1700
Data Index: 6846178 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4326. Min Range: -7.4326
Max Act: 7.1513. Min Act: -0.1700
Data Index: 8279235 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4326. Min Range: -7.4326
Max Act: 7.1201. Min Act: -0.1700
Data Index: 6435090 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4326. Min Range: -7.4326
Max Act: 7.1201. Min Act: -0.1700
Data Index: 5093688 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4326. Min Range: -7.4326
Max Act: 7.1201. Min Act: -0.1700
Data Index: 6130601 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4326. Min Range: -7.4326
Max Act: 7.1201. Min Act: -0.1700
Data Index: 3358637 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4326. Min Range: -7.4326
Max Act: 7.1201. Min Act: -0.1700
Data Index: 1768388 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4326. Min Range: -7.4326
Max Act: 7.0888. Min Act: -0.1700
Data Index: 1846482 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4326. Min Range: -7.4326
Max Act: 7.0888. Min Act: -0.1699
Data Index: 2266504 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4326. Min Range: -7.4326
Max Act: 7.0888. Min Act: -0.1700
Data Index: 7665802 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4326. Min Range: -7.4326
Max Act: 7.0888. Min Act: -0.1700
Data Index: 3049541 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4326. Min Range: -7.4326
Max Act: 7.0576. Min Act: -0.1700
Data Index: 1187592 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4326. Min Range: -7.4326
Max Act: 6.9951. Min Act: -0.1700
Data Index: 1141501 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4326. Min Range: -7.4326
Max Act: 6.9951. Min Act: -0.1700
Data Index: 7585261 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4326. Min Range: -7.4326
Max Act: 6.9638. Min Act: -0.1700
Data Index: 2612034 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4326. Min Range: -7.4326
Max Act: 6.9638. Min Act: -0.1700
Data Index: 4971760 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #19