Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2835 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7955. Min Range: -6.7955
Max Act: 6.7955. Min Act: -0.1700
Data Index: 3583346 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7955. Min Range: -6.7955
Max Act: 6.7643. Min Act: -0.1700
Data Index: 3908454 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7955. Min Range: -6.7955
Max Act: 6.7330. Min Act: -0.1700
Data Index: 588480 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7955. Min Range: -6.7955
Max Act: 6.6705. Min Act: -0.1700
Data Index: 3963189 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7955. Min Range: -6.7955
Max Act: 6.6393. Min Act: -0.1700
Data Index: 5665498 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7955. Min Range: -6.7955
Max Act: 6.6080. Min Act: -0.1700
Data Index: 2309964 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7955. Min Range: -6.7955
Max Act: 6.5768. Min Act: -0.1700
Data Index: 697066 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7955. Min Range: -6.7955
Max Act: 6.6080. Min Act: -0.1700
Data Index: 2745494 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7955. Min Range: -6.7955
Max Act: 6.5455. Min Act: -0.1700
Data Index: 4255280 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7955. Min Range: -6.7955
Max Act: 6.5455. Min Act: -0.1700
Data Index: 3352101 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7955. Min Range: -6.7955
Max Act: 6.4518. Min Act: -0.1700
Data Index: 725395 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7955. Min Range: -6.7955
Max Act: 6.4830. Min Act: -0.1700
Data Index: 315829 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7955. Min Range: -6.7955
Max Act: 6.4205. Min Act: -0.1700
Data Index: 1432288 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7955. Min Range: -6.7955
Max Act: 6.3893. Min Act: -0.1700
Data Index: 5146810 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7955. Min Range: -6.7955
Max Act: 6.4205. Min Act: -0.1700
Data Index: 5208601 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7955. Min Range: -6.7955
Max Act: 6.3893. Min Act: -0.1700
Data Index: 4168928 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7955. Min Range: -6.7955
Max Act: 6.3580. Min Act: -0.1700
Data Index: 5105015 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7955. Min Range: -6.7955
Max Act: 6.3580. Min Act: -0.1700
Data Index: 1189708 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7955. Min Range: -6.7955
Max Act: 6.3580. Min Act: -0.1700
Data Index: 5686296 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7955. Min Range: -6.7955
Max Act: 6.2955. Min Act: -0.1700
Data Index: 3280818 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #19