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

Dataset: Open Web Text

Neuron 2469 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: 1.9456. Min Range: -1.9456

Max Act: 1.9456. Min Act: -0.1700

Data Index: 6176407 (Open Web Text)

Max Activating Token Index: 341

Text #1

Max Range: 1.9456. Min Range: -1.9456

Max Act: 1.8718. Min Act: -0.1700

Data Index: 4896029 (Open Web Text)

Max Activating Token Index: 699

Text #2

Max Range: 1.9456. Min Range: -1.9456

Max Act: 1.8544. Min Act: -0.1700

Data Index: 4108656 (Open Web Text)

Max Activating Token Index: 55

Text #3

Max Range: 1.9456. Min Range: -1.9456

Max Act: 1.8682. Min Act: -0.1700

Data Index: 394149 (Open Web Text)

Max Activating Token Index: 839

Text #4

Max Range: 1.9456. Min Range: -1.9456

Max Act: 1.7927. Min Act: -0.1700

Data Index: 301261 (Open Web Text)

Max Activating Token Index: 186

Text #5

Max Range: 1.9456. Min Range: -1.9456

Max Act: 1.7731. Min Act: -0.1700

Data Index: 1276084 (Open Web Text)

Max Activating Token Index: 672

Text #6

Max Range: 1.9456. Min Range: -1.9456

Max Act: 1.7771. Min Act: -0.1700

Data Index: 8474137 (Open Web Text)

Max Activating Token Index: 59

Text #7

Max Range: 1.9456. Min Range: -1.9456

Max Act: 1.7650. Min Act: -0.1700

Data Index: 2188359 (Open Web Text)

Max Activating Token Index: 652

Text #8

Max Range: 1.9456. Min Range: -1.9456

Max Act: 1.7676. Min Act: -0.1700

Data Index: 2329371 (Open Web Text)

Max Activating Token Index: 414

Text #9

Max Range: 1.9456. Min Range: -1.9456

Max Act: 1.7735. Min Act: -0.1700

Data Index: 269425 (Open Web Text)

Max Activating Token Index: 562

Text #10

Max Range: 1.9456. Min Range: -1.9456

Max Act: 1.7494. Min Act: -0.1700

Data Index: 7914122 (Open Web Text)

Max Activating Token Index: 524

Text #11

Max Range: 1.9456. Min Range: -1.9456

Max Act: 1.7623. Min Act: -0.1700

Data Index: 718156 (Open Web Text)

Max Activating Token Index: 223

Text #12

Max Range: 1.9456. Min Range: -1.9456

Max Act: 1.7557. Min Act: -0.1700

Data Index: 640008 (Open Web Text)

Max Activating Token Index: 755

Text #13

Max Range: 1.9456. Min Range: -1.9456

Max Act: 1.7446. Min Act: -0.1700

Data Index: 4489353 (Open Web Text)

Max Activating Token Index: 436

Text #14

Max Range: 1.9456. Min Range: -1.9456

Max Act: 1.7367. Min Act: -0.1700

Data Index: 6747267 (Open Web Text)

Max Activating Token Index: 633

Text #15

Max Range: 1.9456. Min Range: -1.9456

Max Act: 1.7386. Min Act: -0.1700

Data Index: 8754640 (Open Web Text)

Max Activating Token Index: 298

Text #16

Max Range: 1.9456. Min Range: -1.9456

Max Act: 1.7366. Min Act: -0.1700

Data Index: 2030739 (Open Web Text)

Max Activating Token Index: 69

Text #17

Max Range: 1.9456. Min Range: -1.9456

Max Act: 1.7139. Min Act: -0.1700

Data Index: 285096 (Open Web Text)

Max Activating Token Index: 30

Text #18

Max Range: 1.9456. Min Range: -1.9456

Max Act: 1.7312. Min Act: -0.1700

Data Index: 2367609 (Open Web Text)

Max Activating Token Index: 200

Text #19

Max Range: 1.9456. Min Range: -1.9456

Max Act: 1.7208. Min Act: -0.1700

Data Index: 7182125 (Open Web Text)

Max Activating Token Index: 243