Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2458 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 1.9919. Min Range: -1.9919

Max Act: 1.9878. Min Act: -0.1700

Data Index: 5528443 (Open Web Text)

Max Activating Token Index: 503

Text #1

Max Range: 1.9919. Min Range: -1.9919

Max Act: 1.9919. Min Act: -0.1700

Data Index: 3255499 (Open Web Text)

Max Activating Token Index: 774

Text #2

Max Range: 1.9919. Min Range: -1.9919

Max Act: 1.9444. Min Act: -0.1700

Data Index: 2195066 (Open Web Text)

Max Activating Token Index: 357

Text #3

Max Range: 1.9919. Min Range: -1.9919

Max Act: 1.9447. Min Act: -0.1700

Data Index: 803696 (Open Web Text)

Max Activating Token Index: 723

Text #4

Max Range: 1.9919. Min Range: -1.9919

Max Act: 1.9240. Min Act: -0.1700

Data Index: 2195065 (Open Web Text)

Max Activating Token Index: 837

Text #5

Max Range: 1.9919. Min Range: -1.9919

Max Act: 1.9293. Min Act: -0.1700

Data Index: 6056623 (Open Web Text)

Max Activating Token Index: 41

Text #6

Max Range: 1.9919. Min Range: -1.9919

Max Act: 1.9112. Min Act: -0.1700

Data Index: 4070261 (Open Web Text)

Max Activating Token Index: 295

Text #7

Max Range: 1.9919. Min Range: -1.9919

Max Act: 1.9273. Min Act: -0.1700

Data Index: 5623172 (Open Web Text)

Max Activating Token Index: 111

Text #8

Max Range: 1.9919. Min Range: -1.9919

Max Act: 1.9176. Min Act: -0.1700

Data Index: 7944212 (Open Web Text)

Max Activating Token Index: 116

Text #9

Max Range: 1.9919. Min Range: -1.9919

Max Act: 1.9073. Min Act: -0.1700

Data Index: 3933325 (Open Web Text)

Max Activating Token Index: 95

Text #10

Max Range: 1.9919. Min Range: -1.9919

Max Act: 1.8986. Min Act: -0.1700

Data Index: 4315179 (Open Web Text)

Max Activating Token Index: 346

Text #11

Max Range: 1.9919. Min Range: -1.9919

Max Act: 1.8921. Min Act: -0.1700

Data Index: 3532117 (Open Web Text)

Max Activating Token Index: 679

Text #12

Max Range: 1.9919. Min Range: -1.9919

Max Act: 1.8753. Min Act: -0.1700

Data Index: 2757231 (Open Web Text)

Max Activating Token Index: 706

Text #13

Max Range: 1.9919. Min Range: -1.9919

Max Act: 1.8994. Min Act: -0.1700

Data Index: 8673160 (Open Web Text)

Max Activating Token Index: 219

Text #14

Max Range: 1.9919. Min Range: -1.9919

Max Act: 1.8929. Min Act: -0.1700

Data Index: 8774518 (Open Web Text)

Max Activating Token Index: 248

Text #15

Max Range: 1.9919. Min Range: -1.9919

Max Act: 1.8847. Min Act: -0.1700

Data Index: 8755762 (Open Web Text)

Max Activating Token Index: 1017

Text #16

Max Range: 1.9919. Min Range: -1.9919

Max Act: 1.8859. Min Act: -0.1700

Data Index: 5249530 (Open Web Text)

Max Activating Token Index: 812

Text #17

Max Range: 1.9919. Min Range: -1.9919

Max Act: 1.8786. Min Act: -0.1700

Data Index: 8638933 (Open Web Text)

Max Activating Token Index: 90

Text #18

Max Range: 1.9919. Min Range: -1.9919

Max Act: 1.8928. Min Act: -0.1700

Data Index: 7927438 (Open Web Text)

Max Activating Token Index: 325

Text #19

Max Range: 1.9919. Min Range: -1.9919

Max Act: 1.8917. Min Act: -0.1700

Data Index: 7456369 (Open Web Text)

Max Activating Token Index: 406