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

Dataset: Open Web Text

Neuron 668 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: 4.3147. Min Range: -4.3147

Max Act: 4.3147. Min Act: -0.1700

Data Index: 8403616 (Open Web Text)

Max Activating Token Index: 986

Text #1

Max Range: 4.3147. Min Range: -4.3147

Max Act: 4.2902. Min Act: -0.1700

Data Index: 6339777 (Open Web Text)

Max Activating Token Index: 292

Text #2

Max Range: 4.3147. Min Range: -4.3147

Max Act: 4.2924. Min Act: -0.1700

Data Index: 5280823 (Open Web Text)

Max Activating Token Index: 308

Text #3

Max Range: 4.3147. Min Range: -4.3147

Max Act: 4.2858. Min Act: -0.1700

Data Index: 7632851 (Open Web Text)

Max Activating Token Index: 316

Text #4

Max Range: 4.3147. Min Range: -4.3147

Max Act: 4.2428. Min Act: -0.1700

Data Index: 5402347 (Open Web Text)

Max Activating Token Index: 642

Text #5

Max Range: 4.3147. Min Range: -4.3147

Max Act: 4.2235. Min Act: -0.1700

Data Index: 1513956 (Open Web Text)

Max Activating Token Index: 103

Text #6

Max Range: 4.3147. Min Range: -4.3147

Max Act: 4.1864. Min Act: -0.1700

Data Index: 8083233 (Open Web Text)

Max Activating Token Index: 340

Text #7

Max Range: 4.3147. Min Range: -4.3147

Max Act: 4.1592. Min Act: -0.1700

Data Index: 878191 (Open Web Text)

Max Activating Token Index: 981

Text #8

Max Range: 4.3147. Min Range: -4.3147

Max Act: 4.1572. Min Act: -0.1700

Data Index: 4877332 (Open Web Text)

Max Activating Token Index: 335

Text #9

Max Range: 4.3147. Min Range: -4.3147

Max Act: 4.1603. Min Act: -0.1700

Data Index: 3430212 (Open Web Text)

Max Activating Token Index: 266

Text #10

Max Range: 4.3147. Min Range: -4.3147

Max Act: 4.1891. Min Act: -0.1700

Data Index: 2715422 (Open Web Text)

Max Activating Token Index: 627

Text #11

Max Range: 4.3147. Min Range: -4.3147

Max Act: 4.1271. Min Act: -0.1700

Data Index: 4852202 (Open Web Text)

Max Activating Token Index: 317

Text #12

Max Range: 4.3147. Min Range: -4.3147

Max Act: 4.1455. Min Act: -0.1700

Data Index: 6385507 (Open Web Text)

Max Activating Token Index: 948

Text #13

Max Range: 4.3147. Min Range: -4.3147

Max Act: 4.1190. Min Act: -0.1700

Data Index: 1312898 (Open Web Text)

Max Activating Token Index: 289

Text #14

Max Range: 4.3147. Min Range: -4.3147

Max Act: 4.1140. Min Act: -0.1700

Data Index: 4376097 (Open Web Text)

Max Activating Token Index: 627

Text #15

Max Range: 4.3147. Min Range: -4.3147

Max Act: 4.1051. Min Act: -0.1700

Data Index: 7428502 (Open Web Text)

Max Activating Token Index: 161

Text #16

Max Range: 4.3147. Min Range: -4.3147

Max Act: 4.1151. Min Act: -0.1700

Data Index: 8050176 (Open Web Text)

Max Activating Token Index: 655

Text #17

Max Range: 4.3147. Min Range: -4.3147

Max Act: 4.0905. Min Act: -0.1700

Data Index: 3251530 (Open Web Text)

Max Activating Token Index: 333

Text #18

Max Range: 4.3147. Min Range: -4.3147

Max Act: 4.1054. Min Act: -0.1700

Data Index: 3224097 (Open Web Text)

Max Activating Token Index: 32

Text #19

Max Range: 4.3147. Min Range: -4.3147

Max Act: 4.0692. Min Act: -0.1700

Data Index: 4839757 (Open Web Text)

Max Activating Token Index: 494