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

Dataset: Open Web Text

Neuron 987 in Layer 4

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: 3.4234. Min Range: -3.4234

Max Act: 3.3819. Min Act: -0.1700

Data Index: 6782801 (Open Web Text)

Max Activating Token Index: 351

Text #1

Max Range: 3.4234. Min Range: -3.4234

Max Act: 3.4234. Min Act: -0.1700

Data Index: 6572536 (Open Web Text)

Max Activating Token Index: 90

Text #2

Max Range: 3.4234. Min Range: -3.4234

Max Act: 3.3827. Min Act: -0.1700

Data Index: 2810411 (Open Web Text)

Max Activating Token Index: 406

Text #3

Max Range: 3.4234. Min Range: -3.4234

Max Act: 3.3475. Min Act: -0.1700

Data Index: 3453031 (Open Web Text)

Max Activating Token Index: 610

Text #4

Max Range: 3.4234. Min Range: -3.4234

Max Act: 3.3433. Min Act: -0.1700

Data Index: 8188559 (Open Web Text)

Max Activating Token Index: 184

Text #5

Max Range: 3.4234. Min Range: -3.4234

Max Act: 3.3272. Min Act: -0.1700

Data Index: 657776 (Open Web Text)

Max Activating Token Index: 838

Text #6

Max Range: 3.4234. Min Range: -3.4234

Max Act: 3.2482. Min Act: -0.1700

Data Index: 4633849 (Open Web Text)

Max Activating Token Index: 143

Text #7

Max Range: 3.4234. Min Range: -3.4234

Max Act: 3.2784. Min Act: -0.1700

Data Index: 3401950 (Open Web Text)

Max Activating Token Index: 78

Text #8

Max Range: 3.4234. Min Range: -3.4234

Max Act: 3.2460. Min Act: -0.1700

Data Index: 8191152 (Open Web Text)

Max Activating Token Index: 767

Text #9

Max Range: 3.4234. Min Range: -3.4234

Max Act: 3.2552. Min Act: -0.1700

Data Index: 897903 (Open Web Text)

Max Activating Token Index: 317

Text #10

Max Range: 3.4234. Min Range: -3.4234

Max Act: 3.2607. Min Act: -0.1700

Data Index: 2910265 (Open Web Text)

Max Activating Token Index: 72

Text #11

Max Range: 3.4234. Min Range: -3.4234

Max Act: 3.2403. Min Act: -0.1700

Data Index: 1904729 (Open Web Text)

Max Activating Token Index: 315

Text #12

Max Range: 3.4234. Min Range: -3.4234

Max Act: 3.2313. Min Act: -0.1700

Data Index: 7433228 (Open Web Text)

Max Activating Token Index: 276

Text #13

Max Range: 3.4234. Min Range: -3.4234

Max Act: 3.2397. Min Act: -0.1700

Data Index: 6159321 (Open Web Text)

Max Activating Token Index: 82

Text #14

Max Range: 3.4234. Min Range: -3.4234

Max Act: 3.2012. Min Act: -0.1700

Data Index: 314349 (Open Web Text)

Max Activating Token Index: 702

Text #15

Max Range: 3.4234. Min Range: -3.4234

Max Act: 3.2319. Min Act: -0.1700

Data Index: 3816744 (Open Web Text)

Max Activating Token Index: 365

Text #16

Max Range: 3.4234. Min Range: -3.4234

Max Act: 3.2434. Min Act: -0.1700

Data Index: 3743426 (Open Web Text)

Max Activating Token Index: 775

Text #17

Max Range: 3.4234. Min Range: -3.4234

Max Act: 3.2178. Min Act: -0.1700

Data Index: 8436060 (Open Web Text)

Max Activating Token Index: 738

Text #18

Max Range: 3.4234. Min Range: -3.4234

Max Act: 3.2125. Min Act: -0.1700

Data Index: 5243448 (Open Web Text)

Max Activating Token Index: 314

Text #19

Max Range: 3.4234. Min Range: -3.4234

Max Act: 3.1761. Min Act: -0.1700

Data Index: 7817674 (Open Web Text)

Max Activating Token Index: 502