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

Dataset: Open Web Text

Neuron 401 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: 3.6487. Min Range: -3.6487

Max Act: 3.6333. Min Act: -0.1700

Data Index: 110490 (Open Web Text)

Max Activating Token Index: 513

Text #1

Max Range: 3.6487. Min Range: -3.6487

Max Act: 3.6487. Min Act: -0.1700

Data Index: 1239321 (Open Web Text)

Max Activating Token Index: 443

Text #2

Max Range: 3.6487. Min Range: -3.6487

Max Act: 3.6214. Min Act: -0.1700

Data Index: 6027424 (Open Web Text)

Max Activating Token Index: 699

Text #3

Max Range: 3.6487. Min Range: -3.6487

Max Act: 3.5028. Min Act: -0.1700

Data Index: 389647 (Open Web Text)

Max Activating Token Index: 17

Text #4

Max Range: 3.6487. Min Range: -3.6487

Max Act: 3.4795. Min Act: -0.1700

Data Index: 1618272 (Open Web Text)

Max Activating Token Index: 993

Text #5

Max Range: 3.6487. Min Range: -3.6487

Max Act: 3.4979. Min Act: -0.1700

Data Index: 5419146 (Open Web Text)

Max Activating Token Index: 542

Text #6

Max Range: 3.6487. Min Range: -3.6487

Max Act: 3.4642. Min Act: -0.1700

Data Index: 4087969 (Open Web Text)

Max Activating Token Index: 946

Text #7

Max Range: 3.6487. Min Range: -3.6487

Max Act: 3.4332. Min Act: -0.1700

Data Index: 6882265 (Open Web Text)

Max Activating Token Index: 894

Text #8

Max Range: 3.6487. Min Range: -3.6487

Max Act: 3.4309. Min Act: -0.1700

Data Index: 2733264 (Open Web Text)

Max Activating Token Index: 297

Text #9

Max Range: 3.6487. Min Range: -3.6487

Max Act: 3.4226. Min Act: -0.1700

Data Index: 1961594 (Open Web Text)

Max Activating Token Index: 455

Text #10

Max Range: 3.6487. Min Range: -3.6487

Max Act: 3.4148. Min Act: -0.1700

Data Index: 8036389 (Open Web Text)

Max Activating Token Index: 478

Text #11

Max Range: 3.6487. Min Range: -3.6487

Max Act: 3.4161. Min Act: -0.1700

Data Index: 1019335 (Open Web Text)

Max Activating Token Index: 344

Text #12

Max Range: 3.6487. Min Range: -3.6487

Max Act: 3.4169. Min Act: -0.1700

Data Index: 1836548 (Open Web Text)

Max Activating Token Index: 359

Text #13

Max Range: 3.6487. Min Range: -3.6487

Max Act: 3.4003. Min Act: -0.1700

Data Index: 3900146 (Open Web Text)

Max Activating Token Index: 253

Text #14

Max Range: 3.6487. Min Range: -3.6487

Max Act: 3.4047. Min Act: -0.1700

Data Index: 2415137 (Open Web Text)

Max Activating Token Index: 688

Text #15

Max Range: 3.6487. Min Range: -3.6487

Max Act: 3.4216. Min Act: -0.1700

Data Index: 6646434 (Open Web Text)

Max Activating Token Index: 985

Text #16

Max Range: 3.6487. Min Range: -3.6487

Max Act: 3.4255. Min Act: -0.1700

Data Index: 6373028 (Open Web Text)

Max Activating Token Index: 551

Text #17

Max Range: 3.6487. Min Range: -3.6487

Max Act: 3.4138. Min Act: -0.1700

Data Index: 6480845 (Open Web Text)

Max Activating Token Index: 962

Text #18

Max Range: 3.6487. Min Range: -3.6487

Max Act: 3.4057. Min Act: -0.1700

Data Index: 1804587 (Open Web Text)

Max Activating Token Index: 761

Text #19

Max Range: 3.6487. Min Range: -3.6487

Max Act: 3.4074. Min Act: -0.1700

Data Index: 4624062 (Open Web Text)

Max Activating Token Index: 58