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

Dataset: Open Web Text

Neuron 641 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: 1.9514. Min Range: -1.9514

Max Act: 1.9514. Min Act: -0.1700

Data Index: 207332 (Open Web Text)

Max Activating Token Index: 13

Text #1

Max Range: 1.9514. Min Range: -1.9514

Max Act: 1.8934. Min Act: -0.1700

Data Index: 65181 (Open Web Text)

Max Activating Token Index: 167

Text #2

Max Range: 1.9514. Min Range: -1.9514

Max Act: 1.8774. Min Act: -0.1700

Data Index: 3901907 (Open Web Text)

Max Activating Token Index: 431

Text #3

Max Range: 1.9514. Min Range: -1.9514

Max Act: 1.8638. Min Act: -0.1700

Data Index: 7969493 (Open Web Text)

Max Activating Token Index: 730

Text #4

Max Range: 1.9514. Min Range: -1.9514

Max Act: 1.8471. Min Act: -0.1700

Data Index: 8198269 (Open Web Text)

Max Activating Token Index: 41

Text #5

Max Range: 1.9514. Min Range: -1.9514

Max Act: 1.8503. Min Act: -0.1700

Data Index: 7499528 (Open Web Text)

Max Activating Token Index: 801

Text #6

Max Range: 1.9514. Min Range: -1.9514

Max Act: 1.8452. Min Act: -0.1700

Data Index: 4325030 (Open Web Text)

Max Activating Token Index: 40

Text #7

Max Range: 1.9514. Min Range: -1.9514

Max Act: 1.8457. Min Act: -0.1700

Data Index: 3897813 (Open Web Text)

Max Activating Token Index: 443

Text #8

Max Range: 1.9514. Min Range: -1.9514

Max Act: 1.8420. Min Act: -0.1700

Data Index: 679490 (Open Web Text)

Max Activating Token Index: 558

Text #9

Max Range: 1.9514. Min Range: -1.9514

Max Act: 1.8333. Min Act: -0.1700

Data Index: 7387723 (Open Web Text)

Max Activating Token Index: 112

Text #10

Max Range: 1.9514. Min Range: -1.9514

Max Act: 1.8298. Min Act: -0.1700

Data Index: 5748383 (Open Web Text)

Max Activating Token Index: 142

Text #11

Max Range: 1.9514. Min Range: -1.9514

Max Act: 1.8168. Min Act: -0.1700

Data Index: 3278552 (Open Web Text)

Max Activating Token Index: 218

Text #12

Max Range: 1.9514. Min Range: -1.9514

Max Act: 1.8232. Min Act: -0.1700

Data Index: 891402 (Open Web Text)

Max Activating Token Index: 107

Text #13

Max Range: 1.9514. Min Range: -1.9514

Max Act: 1.8176. Min Act: -0.1700

Data Index: 8639571 (Open Web Text)

Max Activating Token Index: 196

Text #14

Max Range: 1.9514. Min Range: -1.9514

Max Act: 1.8210. Min Act: -0.1700

Data Index: 812466 (Open Web Text)

Max Activating Token Index: 42

Text #15

Max Range: 1.9514. Min Range: -1.9514

Max Act: 1.8082. Min Act: -0.1700

Data Index: 2086868 (Open Web Text)

Max Activating Token Index: 257

Text #16

Max Range: 1.9514. Min Range: -1.9514

Max Act: 1.8187. Min Act: -0.1700

Data Index: 169602 (Open Web Text)

Max Activating Token Index: 710

Text #17

Max Range: 1.9514. Min Range: -1.9514

Max Act: 1.8032. Min Act: -0.1700

Data Index: 4845457 (Open Web Text)

Max Activating Token Index: 128

Text #18

Max Range: 1.9514. Min Range: -1.9514

Max Act: 1.8063. Min Act: -0.1700

Data Index: 3019509 (Open Web Text)

Max Activating Token Index: 75

Text #19

Max Range: 1.9514. Min Range: -1.9514

Max Act: 1.8094. Min Act: -0.1700

Data Index: 3433878 (Open Web Text)

Max Activating Token Index: 431