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

Dataset: Open Web Text

Neuron 1393 in Layer 2

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: 4.3983. Min Range: -4.3983

Max Act: 4.3923. Min Act: -0.1700

Data Index: 4078367 (Open Web Text)

Max Activating Token Index: 533

Text #1

Max Range: 4.3983. Min Range: -4.3983

Max Act: 4.3983. Min Act: -0.1700

Data Index: 12070 (Open Web Text)

Max Activating Token Index: 949

Text #2

Max Range: 4.3983. Min Range: -4.3983

Max Act: 4.3488. Min Act: -0.1700

Data Index: 8246896 (Open Web Text)

Max Activating Token Index: 858

Text #3

Max Range: 4.3983. Min Range: -4.3983

Max Act: 4.3764. Min Act: -0.1700

Data Index: 3627149 (Open Web Text)

Max Activating Token Index: 349

Text #4

Max Range: 4.3983. Min Range: -4.3983

Max Act: 4.3739. Min Act: -0.1700

Data Index: 1936823 (Open Web Text)

Max Activating Token Index: 603

Text #5

Max Range: 4.3983. Min Range: -4.3983

Max Act: 4.3201. Min Act: -0.1693

Data Index: 3594030 (Open Web Text)

Max Activating Token Index: 436

Text #6

Max Range: 4.3983. Min Range: -4.3983

Max Act: 4.3153. Min Act: -0.1698

Data Index: 2092224 (Open Web Text)

Max Activating Token Index: 333

Text #7

Max Range: 4.3983. Min Range: -4.3983

Max Act: 4.3132. Min Act: -0.1698

Data Index: 7564610 (Open Web Text)

Max Activating Token Index: 587

Text #8

Max Range: 4.3983. Min Range: -4.3983

Max Act: 4.2739. Min Act: -0.1700

Data Index: 5317148 (Open Web Text)

Max Activating Token Index: 222

Text #9

Max Range: 4.3983. Min Range: -4.3983

Max Act: 4.2485. Min Act: -0.1699

Data Index: 6825354 (Open Web Text)

Max Activating Token Index: 572

Text #10

Max Range: 4.3983. Min Range: -4.3983

Max Act: 4.2893. Min Act: -0.1700

Data Index: 884399 (Open Web Text)

Max Activating Token Index: 262

Text #11

Max Range: 4.3983. Min Range: -4.3983

Max Act: 4.3036. Min Act: -0.1699

Data Index: 8644171 (Open Web Text)

Max Activating Token Index: 304

Text #12

Max Range: 4.3983. Min Range: -4.3983

Max Act: 4.2787. Min Act: -0.1699

Data Index: 3722671 (Open Web Text)

Max Activating Token Index: 395

Text #13

Max Range: 4.3983. Min Range: -4.3983

Max Act: 4.2873. Min Act: -0.1695

Data Index: 1712329 (Open Web Text)

Max Activating Token Index: 415

Text #14

Max Range: 4.3983. Min Range: -4.3983

Max Act: 4.2625. Min Act: -0.1700

Data Index: 2110189 (Open Web Text)

Max Activating Token Index: 364

Text #15

Max Range: 4.3983. Min Range: -4.3983

Max Act: 4.2388. Min Act: -0.1700

Data Index: 6486783 (Open Web Text)

Max Activating Token Index: 540

Text #16

Max Range: 4.3983. Min Range: -4.3983

Max Act: 4.2840. Min Act: -0.1700

Data Index: 8373810 (Open Web Text)

Max Activating Token Index: 645

Text #17

Max Range: 4.3983. Min Range: -4.3983

Max Act: 4.2464. Min Act: -0.1700

Data Index: 6850120 (Open Web Text)

Max Activating Token Index: 328

Text #18

Max Range: 4.3983. Min Range: -4.3983

Max Act: 4.2229. Min Act: -0.1700

Data Index: 4169754 (Open Web Text)

Max Activating Token Index: 329

Text #19

Max Range: 4.3983. Min Range: -4.3983

Max Act: 4.2352. Min Act: -0.1700

Data Index: 4735967 (Open Web Text)

Max Activating Token Index: 401