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

Dataset: Open Web Text

Neuron 1816 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: 4.4171. Min Range: -4.4171

Max Act: 4.4171. Min Act: -0.1700

Data Index: 2548121 (Open Web Text)

Max Activating Token Index: 129

Text #1

Max Range: 4.4171. Min Range: -4.4171

Max Act: 4.2877. Min Act: -0.1700

Data Index: 1158304 (Open Web Text)

Max Activating Token Index: 171

Text #2

Max Range: 4.4171. Min Range: -4.4171

Max Act: 4.2434. Min Act: -0.1700

Data Index: 822199 (Open Web Text)

Max Activating Token Index: 111

Text #3

Max Range: 4.4171. Min Range: -4.4171

Max Act: 4.2444. Min Act: -0.1700

Data Index: 1018299 (Open Web Text)

Max Activating Token Index: 168

Text #4

Max Range: 4.4171. Min Range: -4.4171

Max Act: 4.2604. Min Act: -0.1700

Data Index: 8389568 (Open Web Text)

Max Activating Token Index: 695

Text #5

Max Range: 4.4171. Min Range: -4.4171

Max Act: 4.2681. Min Act: -0.1700

Data Index: 3497764 (Open Web Text)

Max Activating Token Index: 44

Text #6

Max Range: 4.4171. Min Range: -4.4171

Max Act: 4.2422. Min Act: -0.1700

Data Index: 5154213 (Open Web Text)

Max Activating Token Index: 589

Text #7

Max Range: 4.4171. Min Range: -4.4171

Max Act: 4.2138. Min Act: -0.1700

Data Index: 5251733 (Open Web Text)

Max Activating Token Index: 958

Text #8

Max Range: 4.4171. Min Range: -4.4171

Max Act: 4.2306. Min Act: -0.1700

Data Index: 5422651 (Open Web Text)

Max Activating Token Index: 810

Text #9

Max Range: 4.4171. Min Range: -4.4171

Max Act: 4.2364. Min Act: -0.1700

Data Index: 7793256 (Open Web Text)

Max Activating Token Index: 812

Text #10

Max Range: 4.4171. Min Range: -4.4171

Max Act: 4.2338. Min Act: -0.1700

Data Index: 5063973 (Open Web Text)

Max Activating Token Index: 231

Text #11

Max Range: 4.4171. Min Range: -4.4171

Max Act: 4.2499. Min Act: -0.1700

Data Index: 2756683 (Open Web Text)

Max Activating Token Index: 888

Text #12

Max Range: 4.4171. Min Range: -4.4171

Max Act: 4.2369. Min Act: -0.1700

Data Index: 4568432 (Open Web Text)

Max Activating Token Index: 997

Text #13

Max Range: 4.4171. Min Range: -4.4171

Max Act: 4.2575. Min Act: -0.1700

Data Index: 4345403 (Open Web Text)

Max Activating Token Index: 1005

Text #14

Max Range: 4.4171. Min Range: -4.4171

Max Act: 4.2156. Min Act: -0.1700

Data Index: 8485076 (Open Web Text)

Max Activating Token Index: 222

Text #15

Max Range: 4.4171. Min Range: -4.4171

Max Act: 4.2315. Min Act: -0.1700

Data Index: 341380 (Open Web Text)

Max Activating Token Index: 195

Text #16

Max Range: 4.4171. Min Range: -4.4171

Max Act: 4.2040. Min Act: -0.1700

Data Index: 7171170 (Open Web Text)

Max Activating Token Index: 88

Text #17

Max Range: 4.4171. Min Range: -4.4171

Max Act: 4.2133. Min Act: -0.1700

Data Index: 7214167 (Open Web Text)

Max Activating Token Index: 609

Text #18

Max Range: 4.4171. Min Range: -4.4171

Max Act: 4.2037. Min Act: -0.1700

Data Index: 23177 (Open Web Text)

Max Activating Token Index: 400

Text #19

Max Range: 4.4171. Min Range: -4.4171

Max Act: 4.2173. Min Act: -0.1700

Data Index: 1604769 (Open Web Text)

Max Activating Token Index: 825