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

Dataset: Open Web Text

Neuron 236 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: 1.5323. Min Range: -1.5323

Max Act: 1.5323. Min Act: -0.1698

Data Index: 5429018 (Open Web Text)

Max Activating Token Index: 251

Text #1

Max Range: 1.5323. Min Range: -1.5323

Max Act: 1.5221. Min Act: -0.1700

Data Index: 4810830 (Open Web Text)

Max Activating Token Index: 510

Text #2

Max Range: 1.5323. Min Range: -1.5323

Max Act: 1.4917. Min Act: -0.1700

Data Index: 4125907 (Open Web Text)

Max Activating Token Index: 598

Text #3

Max Range: 1.5323. Min Range: -1.5323

Max Act: 1.4739. Min Act: -0.1700

Data Index: 6934733 (Open Web Text)

Max Activating Token Index: 741

Text #4

Max Range: 1.5323. Min Range: -1.5323

Max Act: 1.4684. Min Act: -0.1696

Data Index: 8421423 (Open Web Text)

Max Activating Token Index: 626

Text #5

Max Range: 1.5323. Min Range: -1.5323

Max Act: 1.4636. Min Act: -0.1700

Data Index: 8385541 (Open Web Text)

Max Activating Token Index: 408

Text #6

Max Range: 1.5323. Min Range: -1.5323

Max Act: 1.4515. Min Act: -0.1699

Data Index: 4611413 (Open Web Text)

Max Activating Token Index: 700

Text #7

Max Range: 1.5323. Min Range: -1.5323

Max Act: 1.4504. Min Act: -0.1700

Data Index: 3441230 (Open Web Text)

Max Activating Token Index: 638

Text #8

Max Range: 1.5323. Min Range: -1.5323

Max Act: 1.4561. Min Act: -0.1700

Data Index: 4408537 (Open Web Text)

Max Activating Token Index: 711

Text #9

Max Range: 1.5323. Min Range: -1.5323

Max Act: 1.4482. Min Act: -0.1662

Data Index: 7224311 (Open Web Text)

Max Activating Token Index: 245

Text #10

Max Range: 1.5323. Min Range: -1.5323

Max Act: 1.4485. Min Act: -0.1700

Data Index: 2059207 (Open Web Text)

Max Activating Token Index: 498

Text #11

Max Range: 1.5323. Min Range: -1.5323

Max Act: 1.4415. Min Act: -0.1698

Data Index: 8421337 (Open Web Text)

Max Activating Token Index: 645

Text #12

Max Range: 1.5323. Min Range: -1.5323

Max Act: 1.4438. Min Act: -0.1700

Data Index: 5975724 (Open Web Text)

Max Activating Token Index: 174

Text #13

Max Range: 1.5323. Min Range: -1.5323

Max Act: 1.4392. Min Act: -0.1700

Data Index: 4825355 (Open Web Text)

Max Activating Token Index: 362

Text #14

Max Range: 1.5323. Min Range: -1.5323

Max Act: 1.4453. Min Act: -0.1693

Data Index: 757386 (Open Web Text)

Max Activating Token Index: 305

Text #15

Max Range: 1.5323. Min Range: -1.5323

Max Act: 1.4375. Min Act: -0.1700

Data Index: 4143497 (Open Web Text)

Max Activating Token Index: 208

Text #16

Max Range: 1.5323. Min Range: -1.5323

Max Act: 1.4238. Min Act: -0.1698

Data Index: 4391529 (Open Web Text)

Max Activating Token Index: 324

Text #17

Max Range: 1.5323. Min Range: -1.5323

Max Act: 1.4294. Min Act: -0.1700

Data Index: 7556190 (Open Web Text)

Max Activating Token Index: 152

Text #18

Max Range: 1.5323. Min Range: -1.5323

Max Act: 1.4301. Min Act: -0.1694

Data Index: 2811818 (Open Web Text)

Max Activating Token Index: 601

Text #19

Max Range: 1.5323. Min Range: -1.5323

Max Act: 1.4291. Min Act: -0.1699

Data Index: 4984575 (Open Web Text)

Max Activating Token Index: 511