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

Dataset: Open Web Text

Neuron 1104 in Layer 5

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: 7.0282. Min Range: -7.0282

Max Act: 7.0126. Min Act: -0.1700

Data Index: 8642989 (Open Web Text)

Max Activating Token Index: 672

Text #1

Max Range: 7.0282. Min Range: -7.0282

Max Act: 7.0282. Min Act: -0.1700

Data Index: 5745091 (Open Web Text)

Max Activating Token Index: 551

Text #2

Max Range: 7.0282. Min Range: -7.0282

Max Act: 6.9725. Min Act: -0.1700

Data Index: 5926597 (Open Web Text)

Max Activating Token Index: 379

Text #3

Max Range: 7.0282. Min Range: -7.0282

Max Act: 6.9802. Min Act: -0.1700

Data Index: 382599 (Open Web Text)

Max Activating Token Index: 707

Text #4

Max Range: 7.0282. Min Range: -7.0282

Max Act: 6.9222. Min Act: -0.1700

Data Index: 3181267 (Open Web Text)

Max Activating Token Index: 242

Text #5

Max Range: 7.0282. Min Range: -7.0282

Max Act: 6.9515. Min Act: -0.1700

Data Index: 3398915 (Open Web Text)

Max Activating Token Index: 670

Text #6

Max Range: 7.0282. Min Range: -7.0282

Max Act: 6.9142. Min Act: -0.1700

Data Index: 8828591 (Open Web Text)

Max Activating Token Index: 818

Text #7

Max Range: 7.0282. Min Range: -7.0282

Max Act: 6.9302. Min Act: -0.1700

Data Index: 7817824 (Open Web Text)

Max Activating Token Index: 552

Text #8

Max Range: 7.0282. Min Range: -7.0282

Max Act: 6.9034. Min Act: -0.1700

Data Index: 5875153 (Open Web Text)

Max Activating Token Index: 205

Text #9

Max Range: 7.0282. Min Range: -7.0282

Max Act: 6.9018. Min Act: -0.1700

Data Index: 3812647 (Open Web Text)

Max Activating Token Index: 190

Text #10

Max Range: 7.0282. Min Range: -7.0282

Max Act: 6.9241. Min Act: -0.1700

Data Index: 8136907 (Open Web Text)

Max Activating Token Index: 702

Text #11

Max Range: 7.0282. Min Range: -7.0282

Max Act: 6.8812. Min Act: -0.1700

Data Index: 389507 (Open Web Text)

Max Activating Token Index: 754

Text #12

Max Range: 7.0282. Min Range: -7.0282

Max Act: 6.8938. Min Act: -0.1700

Data Index: 6792199 (Open Web Text)

Max Activating Token Index: 953

Text #13

Max Range: 7.0282. Min Range: -7.0282

Max Act: 6.8999. Min Act: -0.1700

Data Index: 2449883 (Open Web Text)

Max Activating Token Index: 810

Text #14

Max Range: 7.0282. Min Range: -7.0282

Max Act: 6.8676. Min Act: -0.1700

Data Index: 3888790 (Open Web Text)

Max Activating Token Index: 721

Text #15

Max Range: 7.0282. Min Range: -7.0282

Max Act: 6.8975. Min Act: -0.1700

Data Index: 4087090 (Open Web Text)

Max Activating Token Index: 98

Text #16

Max Range: 7.0282. Min Range: -7.0282

Max Act: 6.8569. Min Act: -0.1700

Data Index: 4128841 (Open Web Text)

Max Activating Token Index: 805

Text #17

Max Range: 7.0282. Min Range: -7.0282

Max Act: 6.8792. Min Act: -0.1700

Data Index: 1254342 (Open Web Text)

Max Activating Token Index: 696

Text #18

Max Range: 7.0282. Min Range: -7.0282

Max Act: 6.8611. Min Act: -0.1700

Data Index: 7686912 (Open Web Text)

Max Activating Token Index: 288

Text #19

Max Range: 7.0282. Min Range: -7.0282

Max Act: 6.8517. Min Act: -0.1700

Data Index: 7153303 (Open Web Text)

Max Activating Token Index: 939