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

Dataset: Open Web Text

Neuron 2234 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: 4.4200. Min Range: -4.4200

Max Act: 4.3849. Min Act: -0.1700

Data Index: 8784211 (Open Web Text)

Max Activating Token Index: 1014

Text #1

Max Range: 4.4200. Min Range: -4.4200

Max Act: 4.4200. Min Act: -0.1700

Data Index: 1180162 (Open Web Text)

Max Activating Token Index: 220

Text #2

Max Range: 4.4200. Min Range: -4.4200

Max Act: 4.3509. Min Act: -0.1700

Data Index: 26728 (Open Web Text)

Max Activating Token Index: 335

Text #3

Max Range: 4.4200. Min Range: -4.4200

Max Act: 4.3457. Min Act: -0.1700

Data Index: 591045 (Open Web Text)

Max Activating Token Index: 529

Text #4

Max Range: 4.4200. Min Range: -4.4200

Max Act: 4.3288. Min Act: -0.1700

Data Index: 8046059 (Open Web Text)

Max Activating Token Index: 577

Text #5

Max Range: 4.4200. Min Range: -4.4200

Max Act: 4.2860. Min Act: -0.1700

Data Index: 1589201 (Open Web Text)

Max Activating Token Index: 556

Text #6

Max Range: 4.4200. Min Range: -4.4200

Max Act: 4.3332. Min Act: -0.1700

Data Index: 4894578 (Open Web Text)

Max Activating Token Index: 287

Text #7

Max Range: 4.4200. Min Range: -4.4200

Max Act: 4.2583. Min Act: -0.1700

Data Index: 1715626 (Open Web Text)

Max Activating Token Index: 524

Text #8

Max Range: 4.4200. Min Range: -4.4200

Max Act: 4.2543. Min Act: -0.1700

Data Index: 7470150 (Open Web Text)

Max Activating Token Index: 372

Text #9

Max Range: 4.4200. Min Range: -4.4200

Max Act: 4.2693. Min Act: -0.1700

Data Index: 1379779 (Open Web Text)

Max Activating Token Index: 270

Text #10

Max Range: 4.4200. Min Range: -4.4200

Max Act: 4.3468. Min Act: -0.1700

Data Index: 351101 (Open Web Text)

Max Activating Token Index: 874

Text #11

Max Range: 4.4200. Min Range: -4.4200

Max Act: 4.3221. Min Act: -0.1700

Data Index: 603568 (Open Web Text)

Max Activating Token Index: 728

Text #12

Max Range: 4.4200. Min Range: -4.4200

Max Act: 4.2440. Min Act: -0.1700

Data Index: 5447504 (Open Web Text)

Max Activating Token Index: 154

Text #13

Max Range: 4.4200. Min Range: -4.4200

Max Act: 4.2158. Min Act: -0.1700

Data Index: 5407392 (Open Web Text)

Max Activating Token Index: 652

Text #14

Max Range: 4.4200. Min Range: -4.4200

Max Act: 4.2592. Min Act: -0.1700

Data Index: 7143230 (Open Web Text)

Max Activating Token Index: 840

Text #15

Max Range: 4.4200. Min Range: -4.4200

Max Act: 4.2521. Min Act: -0.1700

Data Index: 316737 (Open Web Text)

Max Activating Token Index: 426

Text #16

Max Range: 4.4200. Min Range: -4.4200

Max Act: 4.2212. Min Act: -0.1700

Data Index: 5213124 (Open Web Text)

Max Activating Token Index: 839

Text #17

Max Range: 4.4200. Min Range: -4.4200

Max Act: 4.2221. Min Act: -0.1700

Data Index: 4556620 (Open Web Text)

Max Activating Token Index: 801

Text #18

Max Range: 4.4200. Min Range: -4.4200

Max Act: 4.2099. Min Act: -0.1700

Data Index: 1506637 (Open Web Text)

Max Activating Token Index: 635

Text #19

Max Range: 4.4200. Min Range: -4.4200

Max Act: 4.1660. Min Act: -0.1700

Data Index: 1329966 (Open Web Text)

Max Activating Token Index: 84