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

Dataset: Open Web Text

Neuron 971 in Layer 3

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: 3.6640. Min Range: -3.6640

Max Act: 3.6640. Min Act: -0.1700

Data Index: 1749394 (Open Web Text)

Max Activating Token Index: 516

Text #1

Max Range: 3.6640. Min Range: -3.6640

Max Act: 3.5184. Min Act: -0.1700

Data Index: 3007986 (Open Web Text)

Max Activating Token Index: 164

Text #2

Max Range: 3.6640. Min Range: -3.6640

Max Act: 3.4778. Min Act: -0.1700

Data Index: 8025234 (Open Web Text)

Max Activating Token Index: 164

Text #3

Max Range: 3.6640. Min Range: -3.6640

Max Act: 3.4673. Min Act: -0.1700

Data Index: 4649591 (Open Web Text)

Max Activating Token Index: 386

Text #4

Max Range: 3.6640. Min Range: -3.6640

Max Act: 3.4465. Min Act: -0.1700

Data Index: 3623424 (Open Web Text)

Max Activating Token Index: 1022

Text #5

Max Range: 3.6640. Min Range: -3.6640

Max Act: 3.4439. Min Act: -0.1700

Data Index: 177323 (Open Web Text)

Max Activating Token Index: 545

Text #6

Max Range: 3.6640. Min Range: -3.6640

Max Act: 3.4419. Min Act: -0.1700

Data Index: 6618416 (Open Web Text)

Max Activating Token Index: 55

Text #7

Max Range: 3.6640. Min Range: -3.6640

Max Act: 3.4544. Min Act: -0.1700

Data Index: 6129327 (Open Web Text)

Max Activating Token Index: 516

Text #8

Max Range: 3.6640. Min Range: -3.6640

Max Act: 3.4690. Min Act: -0.1700

Data Index: 5064832 (Open Web Text)

Max Activating Token Index: 861

Text #9

Max Range: 3.6640. Min Range: -3.6640

Max Act: 3.4397. Min Act: -0.1700

Data Index: 4941764 (Open Web Text)

Max Activating Token Index: 404

Text #10

Max Range: 3.6640. Min Range: -3.6640

Max Act: 3.4252. Min Act: -0.1700

Data Index: 3880648 (Open Web Text)

Max Activating Token Index: 457

Text #11

Max Range: 3.6640. Min Range: -3.6640

Max Act: 3.4325. Min Act: -0.1700

Data Index: 1647569 (Open Web Text)

Max Activating Token Index: 643

Text #12

Max Range: 3.6640. Min Range: -3.6640

Max Act: 3.4411. Min Act: -0.1700

Data Index: 8022795 (Open Web Text)

Max Activating Token Index: 618

Text #13

Max Range: 3.6640. Min Range: -3.6640

Max Act: 3.4392. Min Act: -0.1700

Data Index: 2772129 (Open Web Text)

Max Activating Token Index: 484

Text #14

Max Range: 3.6640. Min Range: -3.6640

Max Act: 3.4404. Min Act: -0.1700

Data Index: 8025233 (Open Web Text)

Max Activating Token Index: 325

Text #15

Max Range: 3.6640. Min Range: -3.6640

Max Act: 3.4374. Min Act: -0.1700

Data Index: 1920896 (Open Web Text)

Max Activating Token Index: 438

Text #16

Max Range: 3.6640. Min Range: -3.6640

Max Act: 3.4066. Min Act: -0.1700

Data Index: 4643021 (Open Web Text)

Max Activating Token Index: 912

Text #17

Max Range: 3.6640. Min Range: -3.6640

Max Act: 3.4240. Min Act: -0.1700

Data Index: 8069801 (Open Web Text)

Max Activating Token Index: 20

Text #18

Max Range: 3.6640. Min Range: -3.6640

Max Act: 3.4289. Min Act: -0.1700

Data Index: 8315980 (Open Web Text)

Max Activating Token Index: 451

Text #19

Max Range: 3.6640. Min Range: -3.6640

Max Act: 3.4393. Min Act: -0.1700

Data Index: 2651257 (Open Web Text)

Max Activating Token Index: 165