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

Dataset: Open Web Text

Neuron 837 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: 4.3701. Min Range: -4.3701

Max Act: 4.3701. Min Act: -0.1700

Data Index: 2731654 (Open Web Text)

Max Activating Token Index: 537

Text #1

Max Range: 4.3701. Min Range: -4.3701

Max Act: 4.3448. Min Act: -0.1700

Data Index: 8444481 (Open Web Text)

Max Activating Token Index: 988

Text #2

Max Range: 4.3701. Min Range: -4.3701

Max Act: 4.3206. Min Act: -0.1700

Data Index: 4827268 (Open Web Text)

Max Activating Token Index: 492

Text #3

Max Range: 4.3701. Min Range: -4.3701

Max Act: 4.3042. Min Act: -0.1700

Data Index: 4730095 (Open Web Text)

Max Activating Token Index: 111

Text #4

Max Range: 4.3701. Min Range: -4.3701

Max Act: 4.2605. Min Act: -0.1700

Data Index: 6783595 (Open Web Text)

Max Activating Token Index: 1009

Text #5

Max Range: 4.3701. Min Range: -4.3701

Max Act: 4.2454. Min Act: -0.1700

Data Index: 2277164 (Open Web Text)

Max Activating Token Index: 353

Text #6

Max Range: 4.3701. Min Range: -4.3701

Max Act: 4.2217. Min Act: -0.1700

Data Index: 1421836 (Open Web Text)

Max Activating Token Index: 287

Text #7

Max Range: 4.3701. Min Range: -4.3701

Max Act: 4.2190. Min Act: -0.1700

Data Index: 777187 (Open Web Text)

Max Activating Token Index: 873

Text #8

Max Range: 4.3701. Min Range: -4.3701

Max Act: 4.2402. Min Act: -0.1700

Data Index: 4541132 (Open Web Text)

Max Activating Token Index: 109

Text #9

Max Range: 4.3701. Min Range: -4.3701

Max Act: 4.2161. Min Act: -0.1700

Data Index: 8319335 (Open Web Text)

Max Activating Token Index: 396

Text #10

Max Range: 4.3701. Min Range: -4.3701

Max Act: 4.2172. Min Act: -0.1700

Data Index: 8297178 (Open Web Text)

Max Activating Token Index: 21

Text #11

Max Range: 4.3701. Min Range: -4.3701

Max Act: 4.2269. Min Act: -0.1700

Data Index: 6623575 (Open Web Text)

Max Activating Token Index: 626

Text #12

Max Range: 4.3701. Min Range: -4.3701

Max Act: 4.2257. Min Act: -0.1700

Data Index: 5050028 (Open Web Text)

Max Activating Token Index: 716

Text #13

Max Range: 4.3701. Min Range: -4.3701

Max Act: 4.2397. Min Act: -0.1700

Data Index: 3186789 (Open Web Text)

Max Activating Token Index: 424

Text #14

Max Range: 4.3701. Min Range: -4.3701

Max Act: 4.2351. Min Act: -0.1700

Data Index: 1497556 (Open Web Text)

Max Activating Token Index: 412

Text #15

Max Range: 4.3701. Min Range: -4.3701

Max Act: 4.2416. Min Act: -0.1700

Data Index: 921916 (Open Web Text)

Max Activating Token Index: 344

Text #16

Max Range: 4.3701. Min Range: -4.3701

Max Act: 4.2285. Min Act: -0.1700

Data Index: 4306829 (Open Web Text)

Max Activating Token Index: 295

Text #17

Max Range: 4.3701. Min Range: -4.3701

Max Act: 4.1671. Min Act: -0.1700

Data Index: 29908 (Open Web Text)

Max Activating Token Index: 931

Text #18

Max Range: 4.3701. Min Range: -4.3701

Max Act: 4.2028. Min Act: -0.1700

Data Index: 2695312 (Open Web Text)

Max Activating Token Index: 111

Text #19

Max Range: 4.3701. Min Range: -4.3701

Max Act: 4.1622. Min Act: -0.1700

Data Index: 625086 (Open Web Text)

Max Activating Token Index: 752