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

Dataset: Open Web Text

Neuron 468 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: 1.8077. Min Range: -1.8077

Max Act: 1.8077. Min Act: -0.1700

Data Index: 17805 (Open Web Text)

Max Activating Token Index: 511

Text #1

Max Range: 1.8077. Min Range: -1.8077

Max Act: 1.7840. Min Act: -0.1700

Data Index: 4921022 (Open Web Text)

Max Activating Token Index: 15

Text #2

Max Range: 1.8077. Min Range: -1.8077

Max Act: 1.7783. Min Act: -0.1700

Data Index: 5688499 (Open Web Text)

Max Activating Token Index: 160

Text #3

Max Range: 1.8077. Min Range: -1.8077

Max Act: 1.7739. Min Act: -0.1700

Data Index: 3021812 (Open Web Text)

Max Activating Token Index: 166

Text #4

Max Range: 1.8077. Min Range: -1.8077

Max Act: 1.7664. Min Act: -0.1700

Data Index: 689072 (Open Web Text)

Max Activating Token Index: 39

Text #5

Max Range: 1.8077. Min Range: -1.8077

Max Act: 1.7681. Min Act: -0.1700

Data Index: 4834465 (Open Web Text)

Max Activating Token Index: 869

Text #6

Max Range: 1.8077. Min Range: -1.8077

Max Act: 1.7527. Min Act: -0.1700

Data Index: 5981257 (Open Web Text)

Max Activating Token Index: 247

Text #7

Max Range: 1.8077. Min Range: -1.8077

Max Act: 1.7613. Min Act: -0.1700

Data Index: 4632718 (Open Web Text)

Max Activating Token Index: 40

Text #8

Max Range: 1.8077. Min Range: -1.8077

Max Act: 1.7593. Min Act: -0.1700

Data Index: 6536432 (Open Web Text)

Max Activating Token Index: 214

Text #9

Max Range: 1.8077. Min Range: -1.8077

Max Act: 1.7566. Min Act: -0.1700

Data Index: 2788871 (Open Web Text)

Max Activating Token Index: 170

Text #10

Max Range: 1.8077. Min Range: -1.8077

Max Act: 1.7360. Min Act: -0.1700

Data Index: 6097520 (Open Web Text)

Max Activating Token Index: 1012

Text #11

Max Range: 1.8077. Min Range: -1.8077

Max Act: 1.7346. Min Act: -0.1700

Data Index: 6044450 (Open Web Text)

Max Activating Token Index: 12

Text #12

Max Range: 1.8077. Min Range: -1.8077

Max Act: 1.7359. Min Act: -0.1700

Data Index: 1334923 (Open Web Text)

Max Activating Token Index: 330

Text #13

Max Range: 1.8077. Min Range: -1.8077

Max Act: 1.7411. Min Act: -0.1700

Data Index: 461000 (Open Web Text)

Max Activating Token Index: 56

Text #14

Max Range: 1.8077. Min Range: -1.8077

Max Act: 1.7235. Min Act: -0.1700

Data Index: 4393515 (Open Web Text)

Max Activating Token Index: 153

Text #15

Max Range: 1.8077. Min Range: -1.8077

Max Act: 1.7222. Min Act: -0.1700

Data Index: 8507223 (Open Web Text)

Max Activating Token Index: 495

Text #16

Max Range: 1.8077. Min Range: -1.8077

Max Act: 1.7237. Min Act: -0.1700

Data Index: 2018978 (Open Web Text)

Max Activating Token Index: 40

Text #17

Max Range: 1.8077. Min Range: -1.8077

Max Act: 1.7138. Min Act: -0.1700

Data Index: 4351589 (Open Web Text)

Max Activating Token Index: 14

Text #18

Max Range: 1.8077. Min Range: -1.8077

Max Act: 1.7045. Min Act: -0.1700

Data Index: 4815556 (Open Web Text)

Max Activating Token Index: 195

Text #19

Max Range: 1.8077. Min Range: -1.8077

Max Act: 1.7035. Min Act: -0.1700

Data Index: 4135081 (Open Web Text)

Max Activating Token Index: 14