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

Dataset: Open Web Text

Neuron 2523 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: 3.5335. Min Range: -3.5335

Max Act: 3.5335. Min Act: -0.1700

Data Index: 5992434 (Open Web Text)

Max Activating Token Index: 887

Text #1

Max Range: 3.5335. Min Range: -3.5335

Max Act: 3.4022. Min Act: -0.1700

Data Index: 1009347 (Open Web Text)

Max Activating Token Index: 229

Text #2

Max Range: 3.5335. Min Range: -3.5335

Max Act: 3.3774. Min Act: -0.1700

Data Index: 6160279 (Open Web Text)

Max Activating Token Index: 799

Text #3

Max Range: 3.5335. Min Range: -3.5335

Max Act: 3.3203. Min Act: -0.1700

Data Index: 2880245 (Open Web Text)

Max Activating Token Index: 334

Text #4

Max Range: 3.5335. Min Range: -3.5335

Max Act: 3.3204. Min Act: -0.1700

Data Index: 1472811 (Open Web Text)

Max Activating Token Index: 23

Text #5

Max Range: 3.5335. Min Range: -3.5335

Max Act: 3.3221. Min Act: -0.1700

Data Index: 5262110 (Open Web Text)

Max Activating Token Index: 33

Text #6

Max Range: 3.5335. Min Range: -3.5335

Max Act: 3.2968. Min Act: -0.1700

Data Index: 8232480 (Open Web Text)

Max Activating Token Index: 554

Text #7

Max Range: 3.5335. Min Range: -3.5335

Max Act: 3.2885. Min Act: -0.1700

Data Index: 3207620 (Open Web Text)

Max Activating Token Index: 32

Text #8

Max Range: 3.5335. Min Range: -3.5335

Max Act: 3.3044. Min Act: -0.1700

Data Index: 3155286 (Open Web Text)

Max Activating Token Index: 731

Text #9

Max Range: 3.5335. Min Range: -3.5335

Max Act: 3.2690. Min Act: -0.1700

Data Index: 3791195 (Open Web Text)

Max Activating Token Index: 337

Text #10

Max Range: 3.5335. Min Range: -3.5335

Max Act: 3.2634. Min Act: -0.1700

Data Index: 7797858 (Open Web Text)

Max Activating Token Index: 801

Text #11

Max Range: 3.5335. Min Range: -3.5335

Max Act: 3.1847. Min Act: -0.1700

Data Index: 1052326 (Open Web Text)

Max Activating Token Index: 650

Text #12

Max Range: 3.5335. Min Range: -3.5335

Max Act: 3.2712. Min Act: -0.1700

Data Index: 2255462 (Open Web Text)

Max Activating Token Index: 787

Text #13

Max Range: 3.5335. Min Range: -3.5335

Max Act: 3.2446. Min Act: -0.1700

Data Index: 604302 (Open Web Text)

Max Activating Token Index: 532

Text #14

Max Range: 3.5335. Min Range: -3.5335

Max Act: 3.2315. Min Act: -0.1700

Data Index: 4936241 (Open Web Text)

Max Activating Token Index: 283

Text #15

Max Range: 3.5335. Min Range: -3.5335

Max Act: 3.2284. Min Act: -0.1700

Data Index: 2614658 (Open Web Text)

Max Activating Token Index: 354

Text #16

Max Range: 3.5335. Min Range: -3.5335

Max Act: 3.2499. Min Act: -0.1700

Data Index: 7620730 (Open Web Text)

Max Activating Token Index: 429

Text #17

Max Range: 3.5335. Min Range: -3.5335

Max Act: 3.2296. Min Act: -0.1700

Data Index: 3111361 (Open Web Text)

Max Activating Token Index: 254

Text #18

Max Range: 3.5335. Min Range: -3.5335

Max Act: 3.2427. Min Act: -0.1700

Data Index: 8266151 (Open Web Text)

Max Activating Token Index: 43

Text #19

Max Range: 3.5335. Min Range: -3.5335

Max Act: 3.2487. Min Act: -0.1700

Data Index: 1198050 (Open Web Text)

Max Activating Token Index: 810