Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2854 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8422. Min Range: -4.8422
Max Act: 4.8422. Min Act: -0.1700
Data Index: 2497088 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8422. Min Range: -4.8422
Max Act: 4.7172. Min Act: -0.1700
Data Index: 8081699 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8422. Min Range: -4.8422
Max Act: 4.6547. Min Act: -0.1700
Data Index: 7163483 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8422. Min Range: -4.8422
Max Act: 4.6234. Min Act: -0.1700
Data Index: 3656099 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8422. Min Range: -4.8422
Max Act: 4.6234. Min Act: -0.1700
Data Index: 2089199 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8422. Min Range: -4.8422
Max Act: 4.6234. Min Act: -0.1700
Data Index: 3770873 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8422. Min Range: -4.8422
Max Act: 4.6234. Min Act: -0.1700
Data Index: 2620290 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8422. Min Range: -4.8422
Max Act: 4.6234. Min Act: -0.1700
Data Index: 5410018 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8422. Min Range: -4.8422
Max Act: 4.5922. Min Act: -0.1700
Data Index: 7981842 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8422. Min Range: -4.8422
Max Act: 4.6234. Min Act: -0.1700
Data Index: 4626816 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8422. Min Range: -4.8422
Max Act: 4.5922. Min Act: -0.1698
Data Index: 8643540 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8422. Min Range: -4.8422
Max Act: 4.5922. Min Act: -0.1700
Data Index: 6162704 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8422. Min Range: -4.8422
Max Act: 4.5922. Min Act: -0.1700
Data Index: 7849705 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8422. Min Range: -4.8422
Max Act: 4.5922. Min Act: -0.1700
Data Index: 610325 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8422. Min Range: -4.8422
Max Act: 4.5922. Min Act: -0.1700
Data Index: 22480 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8422. Min Range: -4.8422
Max Act: 4.5922. Min Act: -0.1700
Data Index: 810116 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8422. Min Range: -4.8422
Max Act: 4.5922. Min Act: -0.1700
Data Index: 1726090 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8422. Min Range: -4.8422
Max Act: 4.5922. Min Act: -0.1700
Data Index: 6063311 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8422. Min Range: -4.8422
Max Act: 4.5609. Min Act: -0.1700
Data Index: 6162705 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8422. Min Range: -4.8422
Max Act: 4.5609. Min Act: -0.1700
Data Index: 984751 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #19