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

Dataset: Open Web Text

Neuron 1783 in Layer 1

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: 1.7761. Min Range: -1.7761

Max Act: 1.7761. Min Act: -0.1700

Data Index: 6517685 (Open Web Text)

Max Activating Token Index: 340

Text #1

Max Range: 1.7761. Min Range: -1.7761

Max Act: 1.7591. Min Act: -0.1700

Data Index: 3617580 (Open Web Text)

Max Activating Token Index: 639

Text #2

Max Range: 1.7761. Min Range: -1.7761

Max Act: 1.7559. Min Act: -0.1700

Data Index: 4776653 (Open Web Text)

Max Activating Token Index: 704

Text #3

Max Range: 1.7761. Min Range: -1.7761

Max Act: 1.7456. Min Act: -0.1700

Data Index: 6937284 (Open Web Text)

Max Activating Token Index: 212

Text #4

Max Range: 1.7761. Min Range: -1.7761

Max Act: 1.7271. Min Act: -0.1700

Data Index: 2277097 (Open Web Text)

Max Activating Token Index: 447

Text #5

Max Range: 1.7761. Min Range: -1.7761

Max Act: 1.7401. Min Act: -0.1700

Data Index: 5912990 (Open Web Text)

Max Activating Token Index: 389

Text #6

Max Range: 1.7761. Min Range: -1.7761

Max Act: 1.7333. Min Act: -0.1700

Data Index: 2595954 (Open Web Text)

Max Activating Token Index: 181

Text #7

Max Range: 1.7761. Min Range: -1.7761

Max Act: 1.7342. Min Act: -0.1700

Data Index: 5161562 (Open Web Text)

Max Activating Token Index: 302

Text #8

Max Range: 1.7761. Min Range: -1.7761

Max Act: 1.7248. Min Act: -0.1700

Data Index: 2549184 (Open Web Text)

Max Activating Token Index: 116

Text #9

Max Range: 1.7761. Min Range: -1.7761

Max Act: 1.7254. Min Act: -0.1700

Data Index: 5406704 (Open Web Text)

Max Activating Token Index: 136

Text #10

Max Range: 1.7761. Min Range: -1.7761

Max Act: 1.7204. Min Act: -0.1700

Data Index: 8784640 (Open Web Text)

Max Activating Token Index: 940

Text #11

Max Range: 1.7761. Min Range: -1.7761

Max Act: 1.7296. Min Act: -0.1700

Data Index: 2081865 (Open Web Text)

Max Activating Token Index: 27

Text #12

Max Range: 1.7761. Min Range: -1.7761

Max Act: 1.7244. Min Act: -0.1700

Data Index: 7876284 (Open Web Text)

Max Activating Token Index: 234

Text #13

Max Range: 1.7761. Min Range: -1.7761

Max Act: 1.7259. Min Act: -0.1700

Data Index: 7100886 (Open Web Text)

Max Activating Token Index: 561

Text #14

Max Range: 1.7761. Min Range: -1.7761

Max Act: 1.7264. Min Act: -0.1700

Data Index: 1696240 (Open Web Text)

Max Activating Token Index: 102

Text #15

Max Range: 1.7761. Min Range: -1.7761

Max Act: 1.7291. Min Act: -0.1700

Data Index: 4648294 (Open Web Text)

Max Activating Token Index: 280

Text #16

Max Range: 1.7761. Min Range: -1.7761

Max Act: 1.7263. Min Act: -0.1700

Data Index: 1439839 (Open Web Text)

Max Activating Token Index: 157

Text #17

Max Range: 1.7761. Min Range: -1.7761

Max Act: 1.7241. Min Act: -0.1700

Data Index: 6103930 (Open Web Text)

Max Activating Token Index: 671

Text #18

Max Range: 1.7761. Min Range: -1.7761

Max Act: 1.7207. Min Act: -0.1700

Data Index: 3466681 (Open Web Text)

Max Activating Token Index: 252

Text #19

Max Range: 1.7761. Min Range: -1.7761

Max Act: 1.7236. Min Act: -0.1700

Data Index: 1638435 (Open Web Text)

Max Activating Token Index: 406