Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1664 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2772. Min Range: -4.2772
Max Act: 4.2772. Min Act: -0.1700
Data Index: 8360785 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2772. Min Range: -4.2772
Max Act: 4.1209. Min Act: -0.1700
Data Index: 3143373 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2772. Min Range: -4.2772
Max Act: 4.0271. Min Act: -0.1700
Data Index: 5697723 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2772. Min Range: -4.2772
Max Act: 3.7770. Min Act: -0.1700
Data Index: 5662137 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2772. Min Range: -4.2772
Max Act: 3.6988. Min Act: -0.1700
Data Index: 4441490 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2772. Min Range: -4.2772
Max Act: 3.3386. Min Act: -0.1700
Data Index: 2095455 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2772. Min Range: -4.2772
Max Act: 3.3229. Min Act: -0.1700
Data Index: 3551091 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2772. Min Range: -4.2772
Max Act: 3.3072. Min Act: -0.1700
Data Index: 6764153 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2772. Min Range: -4.2772
Max Act: 3.2915. Min Act: -0.1700
Data Index: 4858201 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2772. Min Range: -4.2772
Max Act: 3.3072. Min Act: -0.1700
Data Index: 5983370 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2772. Min Range: -4.2772
Max Act: 3.2758. Min Act: -0.1700
Data Index: 2255377 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2772. Min Range: -4.2772
Max Act: 3.2915. Min Act: -0.1700
Data Index: 8040209 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2772. Min Range: -4.2772
Max Act: 3.2915. Min Act: -0.1700
Data Index: 6693292 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2772. Min Range: -4.2772
Max Act: 3.2601. Min Act: -0.1700
Data Index: 4237041 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2772. Min Range: -4.2772
Max Act: 3.2915. Min Act: -0.1700
Data Index: 5447416 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2772. Min Range: -4.2772
Max Act: 3.2444. Min Act: -0.1700
Data Index: 2972283 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2772. Min Range: -4.2772
Max Act: 3.2601. Min Act: -0.1700
Data Index: 8480780 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2772. Min Range: -4.2772
Max Act: 3.2444. Min Act: -0.1700
Data Index: 738803 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2772. Min Range: -4.2772
Max Act: 3.2444. Min Act: -0.1700
Data Index: 3452413 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2772. Min Range: -4.2772
Max Act: 3.2444. Min Act: -0.1700
Data Index: 1657187 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #19