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

Dataset: Open Web Text

Neuron 1201 in Layer 4

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: 4.6759. Min Range: -4.6759

Max Act: 4.6759. Min Act: -0.1700

Data Index: 1164381 (Open Web Text)

Max Activating Token Index: 686

Text #1

Max Range: 4.6759. Min Range: -4.6759

Max Act: 4.6393. Min Act: -0.1700

Data Index: 3755903 (Open Web Text)

Max Activating Token Index: 43

Text #2

Max Range: 4.6759. Min Range: -4.6759

Max Act: 4.5344. Min Act: -0.1700

Data Index: 724515 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 4.6759. Min Range: -4.6759

Max Act: 4.4692. Min Act: -0.1700

Data Index: 6091240 (Open Web Text)

Max Activating Token Index: 589

Text #4

Max Range: 4.6759. Min Range: -4.6759

Max Act: 4.5010. Min Act: -0.1700

Data Index: 7319005 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 4.6759. Min Range: -4.6759

Max Act: 4.4618. Min Act: -0.1700

Data Index: 2071676 (Open Web Text)

Max Activating Token Index: 902

Text #6

Max Range: 4.6759. Min Range: -4.6759

Max Act: 4.4554. Min Act: -0.1700

Data Index: 1743063 (Open Web Text)

Max Activating Token Index: 541

Text #7

Max Range: 4.6759. Min Range: -4.6759

Max Act: 4.4213. Min Act: -0.1700

Data Index: 4904637 (Open Web Text)

Max Activating Token Index: 560

Text #8

Max Range: 4.6759. Min Range: -4.6759

Max Act: 4.4455. Min Act: -0.1700

Data Index: 4355162 (Open Web Text)

Max Activating Token Index: 682

Text #9

Max Range: 4.6759. Min Range: -4.6759

Max Act: 4.4347. Min Act: -0.1700

Data Index: 1595518 (Open Web Text)

Max Activating Token Index: 1016

Text #10

Max Range: 4.6759. Min Range: -4.6759

Max Act: 4.4536. Min Act: -0.1700

Data Index: 2206468 (Open Web Text)

Max Activating Token Index: 615

Text #11

Max Range: 4.6759. Min Range: -4.6759

Max Act: 4.4603. Min Act: -0.1700

Data Index: 6913088 (Open Web Text)

Max Activating Token Index: 328

Text #12

Max Range: 4.6759. Min Range: -4.6759

Max Act: 4.4502. Min Act: -0.1700

Data Index: 1093497 (Open Web Text)

Max Activating Token Index: 337

Text #13

Max Range: 4.6759. Min Range: -4.6759

Max Act: 4.4165. Min Act: -0.1700

Data Index: 1602117 (Open Web Text)

Max Activating Token Index: 859

Text #14

Max Range: 4.6759. Min Range: -4.6759

Max Act: 4.4117. Min Act: -0.1700

Data Index: 8061213 (Open Web Text)

Max Activating Token Index: 23

Text #15

Max Range: 4.6759. Min Range: -4.6759

Max Act: 4.4214. Min Act: -0.1700

Data Index: 1913049 (Open Web Text)

Max Activating Token Index: 981

Text #16

Max Range: 4.6759. Min Range: -4.6759

Max Act: 4.3900. Min Act: -0.1700

Data Index: 8226959 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 4.6759. Min Range: -4.6759

Max Act: 4.3757. Min Act: -0.1700

Data Index: 5893515 (Open Web Text)

Max Activating Token Index: 526

Text #18

Max Range: 4.6759. Min Range: -4.6759

Max Act: 4.4006. Min Act: -0.1700

Data Index: 5234866 (Open Web Text)

Max Activating Token Index: 503

Text #19

Max Range: 4.6759. Min Range: -4.6759

Max Act: 4.3858. Min Act: -0.1700

Data Index: 8043587 (Open Web Text)

Max Activating Token Index: 150