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

Dataset: Open Web Text

Neuron 66 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: 3.4231. Min Range: -3.4231

Max Act: 3.4231. Min Act: -0.1700

Data Index: 7351877 (Open Web Text)

Max Activating Token Index: 91

Text #1

Max Range: 3.4231. Min Range: -3.4231

Max Act: 3.3560. Min Act: -0.1700

Data Index: 2821552 (Open Web Text)

Max Activating Token Index: 297

Text #2

Max Range: 3.4231. Min Range: -3.4231

Max Act: 3.3675. Min Act: -0.1700

Data Index: 4879785 (Open Web Text)

Max Activating Token Index: 459

Text #3

Max Range: 3.4231. Min Range: -3.4231

Max Act: 3.3594. Min Act: -0.1700

Data Index: 3453074 (Open Web Text)

Max Activating Token Index: 601

Text #4

Max Range: 3.4231. Min Range: -3.4231

Max Act: 3.3060. Min Act: -0.1700

Data Index: 1443967 (Open Web Text)

Max Activating Token Index: 809

Text #5

Max Range: 3.4231. Min Range: -3.4231

Max Act: 3.3794. Min Act: -0.1700

Data Index: 221367 (Open Web Text)

Max Activating Token Index: 726

Text #6

Max Range: 3.4231. Min Range: -3.4231

Max Act: 3.2552. Min Act: -0.1700

Data Index: 3507564 (Open Web Text)

Max Activating Token Index: 393

Text #7

Max Range: 3.4231. Min Range: -3.4231

Max Act: 3.2959. Min Act: -0.1700

Data Index: 8266044 (Open Web Text)

Max Activating Token Index: 196

Text #8

Max Range: 3.4231. Min Range: -3.4231

Max Act: 3.2519. Min Act: -0.1700

Data Index: 8377714 (Open Web Text)

Max Activating Token Index: 951

Text #9

Max Range: 3.4231. Min Range: -3.4231

Max Act: 3.2475. Min Act: -0.1700

Data Index: 769835 (Open Web Text)

Max Activating Token Index: 74

Text #10

Max Range: 3.4231. Min Range: -3.4231

Max Act: 3.2645. Min Act: -0.1700

Data Index: 8021570 (Open Web Text)

Max Activating Token Index: 277

Text #11

Max Range: 3.4231. Min Range: -3.4231

Max Act: 3.2612. Min Act: -0.1700

Data Index: 7048025 (Open Web Text)

Max Activating Token Index: 226

Text #12

Max Range: 3.4231. Min Range: -3.4231

Max Act: 3.2369. Min Act: -0.1700

Data Index: 7899737 (Open Web Text)

Max Activating Token Index: 178

Text #13

Max Range: 3.4231. Min Range: -3.4231

Max Act: 3.2449. Min Act: -0.1700

Data Index: 797300 (Open Web Text)

Max Activating Token Index: 446

Text #14

Max Range: 3.4231. Min Range: -3.4231

Max Act: 3.2441. Min Act: -0.1700

Data Index: 6526953 (Open Web Text)

Max Activating Token Index: 850

Text #15

Max Range: 3.4231. Min Range: -3.4231

Max Act: 3.2198. Min Act: -0.1700

Data Index: 5687895 (Open Web Text)

Max Activating Token Index: 173

Text #16

Max Range: 3.4231. Min Range: -3.4231

Max Act: 3.2150. Min Act: -0.1700

Data Index: 5188360 (Open Web Text)

Max Activating Token Index: 264

Text #17

Max Range: 3.4231. Min Range: -3.4231

Max Act: 3.2222. Min Act: -0.1700

Data Index: 6619136 (Open Web Text)

Max Activating Token Index: 99

Text #18

Max Range: 3.4231. Min Range: -3.4231

Max Act: 3.2046. Min Act: -0.1700

Data Index: 5634888 (Open Web Text)

Max Activating Token Index: 594

Text #19

Max Range: 3.4231. Min Range: -3.4231

Max Act: 3.1912. Min Act: -0.1700

Data Index: 5730658 (Open Web Text)

Max Activating Token Index: 392