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

Dataset: Open Web Text

Neuron 1812 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: 3.4401. Min Range: -3.4401

Max Act: 3.4401. Min Act: -0.1700

Data Index: 2079492 (Open Web Text)

Max Activating Token Index: 458

Text #1

Max Range: 3.4401. Min Range: -3.4401

Max Act: 3.3810. Min Act: -0.1700

Data Index: 2662382 (Open Web Text)

Max Activating Token Index: 886

Text #2

Max Range: 3.4401. Min Range: -3.4401

Max Act: 3.3624. Min Act: -0.1700

Data Index: 2462849 (Open Web Text)

Max Activating Token Index: 72

Text #3

Max Range: 3.4401. Min Range: -3.4401

Max Act: 3.3308. Min Act: -0.1700

Data Index: 3587336 (Open Web Text)

Max Activating Token Index: 538

Text #4

Max Range: 3.4401. Min Range: -3.4401

Max Act: 3.2964. Min Act: -0.1700

Data Index: 7368739 (Open Web Text)

Max Activating Token Index: 1020

Text #5

Max Range: 3.4401. Min Range: -3.4401

Max Act: 3.2825. Min Act: -0.1700

Data Index: 5307342 (Open Web Text)

Max Activating Token Index: 734

Text #6

Max Range: 3.4401. Min Range: -3.4401

Max Act: 3.2717. Min Act: -0.1700

Data Index: 7804976 (Open Web Text)

Max Activating Token Index: 705

Text #7

Max Range: 3.4401. Min Range: -3.4401

Max Act: 3.2639. Min Act: -0.1700

Data Index: 5632297 (Open Web Text)

Max Activating Token Index: 564

Text #8

Max Range: 3.4401. Min Range: -3.4401

Max Act: 3.2667. Min Act: -0.1700

Data Index: 8768158 (Open Web Text)

Max Activating Token Index: 572

Text #9

Max Range: 3.4401. Min Range: -3.4401

Max Act: 3.2277. Min Act: -0.1700

Data Index: 1220762 (Open Web Text)

Max Activating Token Index: 93

Text #10

Max Range: 3.4401. Min Range: -3.4401

Max Act: 3.2425. Min Act: -0.1700

Data Index: 6115852 (Open Web Text)

Max Activating Token Index: 134

Text #11

Max Range: 3.4401. Min Range: -3.4401

Max Act: 3.2347. Min Act: -0.1700

Data Index: 2488702 (Open Web Text)

Max Activating Token Index: 187

Text #12

Max Range: 3.4401. Min Range: -3.4401

Max Act: 3.2394. Min Act: -0.1700

Data Index: 8753824 (Open Web Text)

Max Activating Token Index: 216

Text #13

Max Range: 3.4401. Min Range: -3.4401

Max Act: 3.2275. Min Act: -0.1700

Data Index: 202196 (Open Web Text)

Max Activating Token Index: 102

Text #14

Max Range: 3.4401. Min Range: -3.4401

Max Act: 3.2194. Min Act: -0.1700

Data Index: 4026311 (Open Web Text)

Max Activating Token Index: 421

Text #15

Max Range: 3.4401. Min Range: -3.4401

Max Act: 3.2223. Min Act: -0.1700

Data Index: 5363526 (Open Web Text)

Max Activating Token Index: 255

Text #16

Max Range: 3.4401. Min Range: -3.4401

Max Act: 3.2187. Min Act: -0.1700

Data Index: 641560 (Open Web Text)

Max Activating Token Index: 136

Text #17

Max Range: 3.4401. Min Range: -3.4401

Max Act: 3.2334. Min Act: -0.1700

Data Index: 2356453 (Open Web Text)

Max Activating Token Index: 313

Text #18

Max Range: 3.4401. Min Range: -3.4401

Max Act: 3.2207. Min Act: -0.1700

Data Index: 2409680 (Open Web Text)

Max Activating Token Index: 408

Text #19

Max Range: 3.4401. Min Range: -3.4401

Max Act: 3.2309. Min Act: -0.1700

Data Index: 3906384 (Open Web Text)

Max Activating Token Index: 239