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

Dataset: Open Web Text

Neuron 2129 in Layer 6

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: 2.5320. Min Range: -2.5320

Max Act: 2.5320. Min Act: -0.1700

Data Index: 731889 (Open Web Text)

Max Activating Token Index: 658

Text #1

Max Range: 2.5320. Min Range: -2.5320

Max Act: 2.5207. Min Act: -0.1700

Data Index: 8691915 (Open Web Text)

Max Activating Token Index: 541

Text #2

Max Range: 2.5320. Min Range: -2.5320

Max Act: 2.5129. Min Act: -0.1700

Data Index: 5234494 (Open Web Text)

Max Activating Token Index: 567

Text #3

Max Range: 2.5320. Min Range: -2.5320

Max Act: 2.5109. Min Act: -0.1700

Data Index: 1110021 (Open Web Text)

Max Activating Token Index: 225

Text #4

Max Range: 2.5320. Min Range: -2.5320

Max Act: 2.5069. Min Act: -0.1700

Data Index: 4430187 (Open Web Text)

Max Activating Token Index: 681

Text #5

Max Range: 2.5320. Min Range: -2.5320

Max Act: 2.4622. Min Act: -0.1700

Data Index: 2069982 (Open Web Text)

Max Activating Token Index: 417

Text #6

Max Range: 2.5320. Min Range: -2.5320

Max Act: 2.4052. Min Act: -0.1700

Data Index: 7165109 (Open Web Text)

Max Activating Token Index: 814

Text #7

Max Range: 2.5320. Min Range: -2.5320

Max Act: 2.4146. Min Act: -0.1700

Data Index: 2799227 (Open Web Text)

Max Activating Token Index: 80

Text #8

Max Range: 2.5320. Min Range: -2.5320

Max Act: 2.3993. Min Act: -0.1700

Data Index: 3293303 (Open Web Text)

Max Activating Token Index: 662

Text #9

Max Range: 2.5320. Min Range: -2.5320

Max Act: 2.4106. Min Act: -0.1700

Data Index: 766723 (Open Web Text)

Max Activating Token Index: 285

Text #10

Max Range: 2.5320. Min Range: -2.5320

Max Act: 2.3971. Min Act: -0.1700

Data Index: 1684219 (Open Web Text)

Max Activating Token Index: 701

Text #11

Max Range: 2.5320. Min Range: -2.5320

Max Act: 2.3954. Min Act: -0.1700

Data Index: 7766885 (Open Web Text)

Max Activating Token Index: 459

Text #12

Max Range: 2.5320. Min Range: -2.5320

Max Act: 2.3799. Min Act: -0.1700

Data Index: 7941056 (Open Web Text)

Max Activating Token Index: 194

Text #13

Max Range: 2.5320. Min Range: -2.5320

Max Act: 2.3860. Min Act: -0.1700

Data Index: 5102111 (Open Web Text)

Max Activating Token Index: 139

Text #14

Max Range: 2.5320. Min Range: -2.5320

Max Act: 2.3925. Min Act: -0.1700

Data Index: 7251802 (Open Web Text)

Max Activating Token Index: 926

Text #15

Max Range: 2.5320. Min Range: -2.5320

Max Act: 2.4003. Min Act: -0.1700

Data Index: 8201180 (Open Web Text)

Max Activating Token Index: 586

Text #16

Max Range: 2.5320. Min Range: -2.5320

Max Act: 2.3811. Min Act: -0.1700

Data Index: 4171215 (Open Web Text)

Max Activating Token Index: 76

Text #17

Max Range: 2.5320. Min Range: -2.5320

Max Act: 2.3538. Min Act: -0.1700

Data Index: 6512343 (Open Web Text)

Max Activating Token Index: 466

Text #18

Max Range: 2.5320. Min Range: -2.5320

Max Act: 2.3833. Min Act: -0.1700

Data Index: 3451942 (Open Web Text)

Max Activating Token Index: 178

Text #19

Max Range: 2.5320. Min Range: -2.5320

Max Act: 2.3553. Min Act: -0.1700

Data Index: 64413 (Open Web Text)

Max Activating Token Index: 866