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

Dataset: Open Web Text

Neuron 1069 in Layer 1

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: 2.4086. Min Range: -2.4086

Max Act: 2.4086. Min Act: -0.1700

Data Index: 4404378 (Open Web Text)

Max Activating Token Index: 147

Text #1

Max Range: 2.4086. Min Range: -2.4086

Max Act: 2.3109. Min Act: -0.1700

Data Index: 5598307 (Open Web Text)

Max Activating Token Index: 462

Text #2

Max Range: 2.4086. Min Range: -2.4086

Max Act: 2.2852. Min Act: -0.1700

Data Index: 5686949 (Open Web Text)

Max Activating Token Index: 113

Text #3

Max Range: 2.4086. Min Range: -2.4086

Max Act: 2.2548. Min Act: -0.1700

Data Index: 1852495 (Open Web Text)

Max Activating Token Index: 309

Text #4

Max Range: 2.4086. Min Range: -2.4086

Max Act: 2.2294. Min Act: -0.1700

Data Index: 4543581 (Open Web Text)

Max Activating Token Index: 25

Text #5

Max Range: 2.4086. Min Range: -2.4086

Max Act: 2.2348. Min Act: -0.1700

Data Index: 1852497 (Open Web Text)

Max Activating Token Index: 188

Text #6

Max Range: 2.4086. Min Range: -2.4086

Max Act: 2.2011. Min Act: -0.1700

Data Index: 6442520 (Open Web Text)

Max Activating Token Index: 12

Text #7

Max Range: 2.4086. Min Range: -2.4086

Max Act: 2.1870. Min Act: -0.1700

Data Index: 3158070 (Open Web Text)

Max Activating Token Index: 285

Text #8

Max Range: 2.4086. Min Range: -2.4086

Max Act: 2.1646. Min Act: -0.1700

Data Index: 5283701 (Open Web Text)

Max Activating Token Index: 114

Text #9

Max Range: 2.4086. Min Range: -2.4086

Max Act: 2.1449. Min Act: -0.1700

Data Index: 1727499 (Open Web Text)

Max Activating Token Index: 103

Text #10

Max Range: 2.4086. Min Range: -2.4086

Max Act: 2.1635. Min Act: -0.1700

Data Index: 2592324 (Open Web Text)

Max Activating Token Index: 150

Text #11

Max Range: 2.4086. Min Range: -2.4086

Max Act: 2.1342. Min Act: -0.1700

Data Index: 629269 (Open Web Text)

Max Activating Token Index: 454

Text #12

Max Range: 2.4086. Min Range: -2.4086

Max Act: 2.1419. Min Act: -0.1700

Data Index: 3582729 (Open Web Text)

Max Activating Token Index: 947

Text #13

Max Range: 2.4086. Min Range: -2.4086

Max Act: 2.1242. Min Act: -0.1700

Data Index: 2461586 (Open Web Text)

Max Activating Token Index: 460

Text #14

Max Range: 2.4086. Min Range: -2.4086

Max Act: 2.1197. Min Act: -0.1700

Data Index: 4550668 (Open Web Text)

Max Activating Token Index: 378

Text #15

Max Range: 2.4086. Min Range: -2.4086

Max Act: 2.1195. Min Act: -0.1700

Data Index: 5838456 (Open Web Text)

Max Activating Token Index: 404

Text #16

Max Range: 2.4086. Min Range: -2.4086

Max Act: 2.1236. Min Act: -0.1700

Data Index: 7641578 (Open Web Text)

Max Activating Token Index: 630

Text #17

Max Range: 2.4086. Min Range: -2.4086

Max Act: 2.1201. Min Act: -0.1700

Data Index: 7061532 (Open Web Text)

Max Activating Token Index: 430

Text #18

Max Range: 2.4086. Min Range: -2.4086

Max Act: 2.0960. Min Act: -0.1700

Data Index: 977872 (Open Web Text)

Max Activating Token Index: 189

Text #19

Max Range: 2.4086. Min Range: -2.4086

Max Act: 2.0961. Min Act: -0.1700

Data Index: 1852496 (Open Web Text)

Max Activating Token Index: 903