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

Dataset: Open Web Text

Neuron 1840 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: 4.1165. Min Range: -4.1165

Max Act: 4.1122. Min Act: -0.1700

Data Index: 4931902 (Open Web Text)

Max Activating Token Index: 586

Text #1

Max Range: 4.1165. Min Range: -4.1165

Max Act: 4.1165. Min Act: -0.1700

Data Index: 359262 (Open Web Text)

Max Activating Token Index: 391

Text #2

Max Range: 4.1165. Min Range: -4.1165

Max Act: 4.0627. Min Act: -0.1700

Data Index: 7776435 (Open Web Text)

Max Activating Token Index: 366

Text #3

Max Range: 4.1165. Min Range: -4.1165

Max Act: 4.0516. Min Act: -0.1700

Data Index: 4169632 (Open Web Text)

Max Activating Token Index: 508

Text #4

Max Range: 4.1165. Min Range: -4.1165

Max Act: 4.0235. Min Act: -0.1700

Data Index: 5723023 (Open Web Text)

Max Activating Token Index: 341

Text #5

Max Range: 4.1165. Min Range: -4.1165

Max Act: 4.0400. Min Act: -0.1700

Data Index: 2853895 (Open Web Text)

Max Activating Token Index: 716

Text #6

Max Range: 4.1165. Min Range: -4.1165

Max Act: 4.0284. Min Act: -0.1700

Data Index: 6801708 (Open Web Text)

Max Activating Token Index: 296

Text #7

Max Range: 4.1165. Min Range: -4.1165

Max Act: 4.0533. Min Act: -0.1700

Data Index: 6377185 (Open Web Text)

Max Activating Token Index: 837

Text #8

Max Range: 4.1165. Min Range: -4.1165

Max Act: 4.0598. Min Act: -0.1700

Data Index: 3983204 (Open Web Text)

Max Activating Token Index: 73

Text #9

Max Range: 4.1165. Min Range: -4.1165

Max Act: 4.0350. Min Act: -0.1700

Data Index: 2305668 (Open Web Text)

Max Activating Token Index: 233

Text #10

Max Range: 4.1165. Min Range: -4.1165

Max Act: 4.0084. Min Act: -0.1700

Data Index: 6885288 (Open Web Text)

Max Activating Token Index: 605

Text #11

Max Range: 4.1165. Min Range: -4.1165

Max Act: 4.0036. Min Act: -0.1700

Data Index: 7234874 (Open Web Text)

Max Activating Token Index: 425

Text #12

Max Range: 4.1165. Min Range: -4.1165

Max Act: 4.0326. Min Act: -0.1700

Data Index: 6529240 (Open Web Text)

Max Activating Token Index: 479

Text #13

Max Range: 4.1165. Min Range: -4.1165

Max Act: 4.0230. Min Act: -0.1700

Data Index: 1617980 (Open Web Text)

Max Activating Token Index: 342

Text #14

Max Range: 4.1165. Min Range: -4.1165

Max Act: 4.0318. Min Act: -0.1700

Data Index: 8739336 (Open Web Text)

Max Activating Token Index: 88

Text #15

Max Range: 4.1165. Min Range: -4.1165

Max Act: 4.0040. Min Act: -0.1700

Data Index: 1730534 (Open Web Text)

Max Activating Token Index: 729

Text #16

Max Range: 4.1165. Min Range: -4.1165

Max Act: 4.0082. Min Act: -0.1700

Data Index: 2929424 (Open Web Text)

Max Activating Token Index: 466

Text #17

Max Range: 4.1165. Min Range: -4.1165

Max Act: 4.0176. Min Act: -0.1700

Data Index: 6266627 (Open Web Text)

Max Activating Token Index: 631

Text #18

Max Range: 4.1165. Min Range: -4.1165

Max Act: 3.9418. Min Act: -0.1700

Data Index: 2881744 (Open Web Text)

Max Activating Token Index: 747

Text #19

Max Range: 4.1165. Min Range: -4.1165

Max Act: 3.9895. Min Act: -0.1700

Data Index: 2887844 (Open Web Text)

Max Activating Token Index: 605