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

Dataset: Open Web Text

Neuron 389 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: 3.2536. Min Range: -3.2536

Max Act: 3.2536. Min Act: -0.1700

Data Index: 4473618 (Open Web Text)

Max Activating Token Index: 16

Text #1

Max Range: 3.2536. Min Range: -3.2536

Max Act: 3.2042. Min Act: -0.1700

Data Index: 4950600 (Open Web Text)

Max Activating Token Index: 593

Text #2

Max Range: 3.2536. Min Range: -3.2536

Max Act: 3.1302. Min Act: -0.1700

Data Index: 6822133 (Open Web Text)

Max Activating Token Index: 359

Text #3

Max Range: 3.2536. Min Range: -3.2536

Max Act: 3.1220. Min Act: -0.1700

Data Index: 4100058 (Open Web Text)

Max Activating Token Index: 45

Text #4

Max Range: 3.2536. Min Range: -3.2536

Max Act: 3.1074. Min Act: -0.1700

Data Index: 8505271 (Open Web Text)

Max Activating Token Index: 348

Text #5

Max Range: 3.2536. Min Range: -3.2536

Max Act: 3.0940. Min Act: -0.1700

Data Index: 2092643 (Open Web Text)

Max Activating Token Index: 405

Text #6

Max Range: 3.2536. Min Range: -3.2536

Max Act: 3.0719. Min Act: -0.1700

Data Index: 6227430 (Open Web Text)

Max Activating Token Index: 203

Text #7

Max Range: 3.2536. Min Range: -3.2536

Max Act: 3.0893. Min Act: -0.1700

Data Index: 3860520 (Open Web Text)

Max Activating Token Index: 57

Text #8

Max Range: 3.2536. Min Range: -3.2536

Max Act: 3.0378. Min Act: -0.1700

Data Index: 1997443 (Open Web Text)

Max Activating Token Index: 1020

Text #9

Max Range: 3.2536. Min Range: -3.2536

Max Act: 3.0391. Min Act: -0.1700

Data Index: 1446926 (Open Web Text)

Max Activating Token Index: 346

Text #10

Max Range: 3.2536. Min Range: -3.2536

Max Act: 3.0493. Min Act: -0.1700

Data Index: 962423 (Open Web Text)

Max Activating Token Index: 671

Text #11

Max Range: 3.2536. Min Range: -3.2536

Max Act: 3.0527. Min Act: -0.1700

Data Index: 6172116 (Open Web Text)

Max Activating Token Index: 773

Text #12

Max Range: 3.2536. Min Range: -3.2536

Max Act: 3.0405. Min Act: -0.1700

Data Index: 8310239 (Open Web Text)

Max Activating Token Index: 104

Text #13

Max Range: 3.2536. Min Range: -3.2536

Max Act: 3.0293. Min Act: -0.1700

Data Index: 638664 (Open Web Text)

Max Activating Token Index: 258

Text #14

Max Range: 3.2536. Min Range: -3.2536

Max Act: 3.0333. Min Act: -0.1700

Data Index: 8243248 (Open Web Text)

Max Activating Token Index: 117

Text #15

Max Range: 3.2536. Min Range: -3.2536

Max Act: 3.0319. Min Act: -0.1699

Data Index: 5972854 (Open Web Text)

Max Activating Token Index: 194

Text #16

Max Range: 3.2536. Min Range: -3.2536

Max Act: 3.0191. Min Act: -0.1700

Data Index: 4727343 (Open Web Text)

Max Activating Token Index: 864

Text #17

Max Range: 3.2536. Min Range: -3.2536

Max Act: 3.0197. Min Act: -0.1700

Data Index: 8067828 (Open Web Text)

Max Activating Token Index: 53

Text #18

Max Range: 3.2536. Min Range: -3.2536

Max Act: 3.0036. Min Act: -0.1700

Data Index: 4165999 (Open Web Text)

Max Activating Token Index: 87

Text #19

Max Range: 3.2536. Min Range: -3.2536

Max Act: 2.9892. Min Act: -0.1700

Data Index: 7731848 (Open Web Text)

Max Activating Token Index: 173