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

Dataset: Open Web Text

Neuron 248 in Layer 0

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: 1.2968. Min Range: -1.2968

Max Act: 1.2968. Min Act: -0.1673

Data Index: 482320 (Open Web Text)

Max Activating Token Index: 676

Text #1

Max Range: 1.2968. Min Range: -1.2968

Max Act: 1.2895. Min Act: -0.1483

Data Index: 4131067 (Open Web Text)

Max Activating Token Index: 722

Text #2

Max Range: 1.2968. Min Range: -1.2968

Max Act: 1.2916. Min Act: -0.1695

Data Index: 8504752 (Open Web Text)

Max Activating Token Index: 699

Text #3

Max Range: 1.2968. Min Range: -1.2968

Max Act: 1.2587. Min Act: -0.1518

Data Index: 3331999 (Open Web Text)

Max Activating Token Index: 669

Text #4

Max Range: 1.2968. Min Range: -1.2968

Max Act: 1.2593. Min Act: -0.1124

Data Index: 5511597 (Open Web Text)

Max Activating Token Index: 708

Text #5

Max Range: 1.2968. Min Range: -1.2968

Max Act: 1.2431. Min Act: -0.1567

Data Index: 1802936 (Open Web Text)

Max Activating Token Index: 450

Text #6

Max Range: 1.2968. Min Range: -1.2968

Max Act: 1.2457. Min Act: -0.1550

Data Index: 7592153 (Open Web Text)

Max Activating Token Index: 781

Text #7

Max Range: 1.2968. Min Range: -1.2968

Max Act: 1.2393. Min Act: -0.1696

Data Index: 5752806 (Open Web Text)

Max Activating Token Index: 695

Text #8

Max Range: 1.2968. Min Range: -1.2968

Max Act: 1.2343. Min Act: -0.1422

Data Index: 4043246 (Open Web Text)

Max Activating Token Index: 891

Text #9

Max Range: 1.2968. Min Range: -1.2968

Max Act: 1.2313. Min Act: -0.0310

Data Index: 5079296 (Open Web Text)

Max Activating Token Index: 58

Text #10

Max Range: 1.2968. Min Range: -1.2968

Max Act: 1.2262. Min Act: -0.1660

Data Index: 8597412 (Open Web Text)

Max Activating Token Index: 431

Text #11

Max Range: 1.2968. Min Range: -1.2968

Max Act: 1.2314. Min Act: -0.1699

Data Index: 5437035 (Open Web Text)

Max Activating Token Index: 598

Text #12

Max Range: 1.2968. Min Range: -1.2968

Max Act: 1.2298. Min Act: -0.1592

Data Index: 7942561 (Open Web Text)

Max Activating Token Index: 687

Text #13

Max Range: 1.2968. Min Range: -1.2968

Max Act: 1.2226. Min Act: -0.1671

Data Index: 3544895 (Open Web Text)

Max Activating Token Index: 478

Text #14

Max Range: 1.2968. Min Range: -1.2968

Max Act: 1.2233. Min Act: -0.1666

Data Index: 6818475 (Open Web Text)

Max Activating Token Index: 533

Text #15

Max Range: 1.2968. Min Range: -1.2968

Max Act: 1.2140. Min Act: -0.1661

Data Index: 2680651 (Open Web Text)

Max Activating Token Index: 707

Text #16

Max Range: 1.2968. Min Range: -1.2968

Max Act: 1.2248. Min Act: -0.1542

Data Index: 5157880 (Open Web Text)

Max Activating Token Index: 457

Text #17

Max Range: 1.2968. Min Range: -1.2968

Max Act: 1.2209. Min Act: -0.1638

Data Index: 5040930 (Open Web Text)

Max Activating Token Index: 397

Text #18

Max Range: 1.2968. Min Range: -1.2968

Max Act: 1.2215. Min Act: -0.0883

Data Index: 7027614 (Open Web Text)

Max Activating Token Index: 761

Text #19

Max Range: 1.2968. Min Range: -1.2968

Max Act: 1.2095. Min Act: -0.1486

Data Index: 575351 (Open Web Text)

Max Activating Token Index: 686