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

Dataset: Open Web Text

Neuron 2386 in Layer 4

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: 5.4202. Min Range: -5.4202

Max Act: 5.4202. Min Act: -0.1700

Data Index: 1180408 (Open Web Text)

Max Activating Token Index: 229

Text #1

Max Range: 5.4202. Min Range: -5.4202

Max Act: 5.3925. Min Act: -0.1700

Data Index: 2404004 (Open Web Text)

Max Activating Token Index: 352

Text #2

Max Range: 5.4202. Min Range: -5.4202

Max Act: 5.3359. Min Act: -0.1700

Data Index: 5747133 (Open Web Text)

Max Activating Token Index: 284

Text #3

Max Range: 5.4202. Min Range: -5.4202

Max Act: 5.2663. Min Act: -0.1700

Data Index: 339635 (Open Web Text)

Max Activating Token Index: 802

Text #4

Max Range: 5.4202. Min Range: -5.4202

Max Act: 5.2881. Min Act: -0.1700

Data Index: 7632622 (Open Web Text)

Max Activating Token Index: 335

Text #5

Max Range: 5.4202. Min Range: -5.4202

Max Act: 5.2390. Min Act: -0.1700

Data Index: 8510014 (Open Web Text)

Max Activating Token Index: 482

Text #6

Max Range: 5.4202. Min Range: -5.4202

Max Act: 5.2584. Min Act: -0.1700

Data Index: 1494801 (Open Web Text)

Max Activating Token Index: 343

Text #7

Max Range: 5.4202. Min Range: -5.4202

Max Act: 5.2340. Min Act: -0.1700

Data Index: 1260752 (Open Web Text)

Max Activating Token Index: 905

Text #8

Max Range: 5.4202. Min Range: -5.4202

Max Act: 5.1821. Min Act: -0.1700

Data Index: 4526944 (Open Web Text)

Max Activating Token Index: 549

Text #9

Max Range: 5.4202. Min Range: -5.4202

Max Act: 5.1711. Min Act: -0.1700

Data Index: 5616878 (Open Web Text)

Max Activating Token Index: 522

Text #10

Max Range: 5.4202. Min Range: -5.4202

Max Act: 5.1687. Min Act: -0.1700

Data Index: 1335967 (Open Web Text)

Max Activating Token Index: 491

Text #11

Max Range: 5.4202. Min Range: -5.4202

Max Act: 5.2235. Min Act: -0.1700

Data Index: 8079556 (Open Web Text)

Max Activating Token Index: 118

Text #12

Max Range: 5.4202. Min Range: -5.4202

Max Act: 5.1867. Min Act: -0.1700

Data Index: 5550925 (Open Web Text)

Max Activating Token Index: 968

Text #13

Max Range: 5.4202. Min Range: -5.4202

Max Act: 5.1743. Min Act: -0.1700

Data Index: 5146525 (Open Web Text)

Max Activating Token Index: 282

Text #14

Max Range: 5.4202. Min Range: -5.4202

Max Act: 5.1108. Min Act: -0.1700

Data Index: 4499817 (Open Web Text)

Max Activating Token Index: 580

Text #15

Max Range: 5.4202. Min Range: -5.4202

Max Act: 5.1988. Min Act: -0.1700

Data Index: 2649745 (Open Web Text)

Max Activating Token Index: 373

Text #16

Max Range: 5.4202. Min Range: -5.4202

Max Act: 5.0713. Min Act: -0.1699

Data Index: 3650428 (Open Web Text)

Max Activating Token Index: 459

Text #17

Max Range: 5.4202. Min Range: -5.4202

Max Act: 5.1215. Min Act: -0.1700

Data Index: 2936668 (Open Web Text)

Max Activating Token Index: 471

Text #18

Max Range: 5.4202. Min Range: -5.4202

Max Act: 5.1311. Min Act: -0.1700

Data Index: 6098985 (Open Web Text)

Max Activating Token Index: 168

Text #19

Max Range: 5.4202. Min Range: -5.4202

Max Act: 5.1413. Min Act: -0.1699

Data Index: 3788171 (Open Web Text)

Max Activating Token Index: 326