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

Dataset: Open Web Text

Neuron 2853 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: 3.2382. Min Range: -3.2382

Max Act: 3.2382. Min Act: -0.1700

Data Index: 6341817 (Open Web Text)

Max Activating Token Index: 951

Text #1

Max Range: 3.2382. Min Range: -3.2382

Max Act: 3.1484. Min Act: -0.1700

Data Index: 8084550 (Open Web Text)

Max Activating Token Index: 603

Text #2

Max Range: 3.2382. Min Range: -3.2382

Max Act: 3.0848. Min Act: -0.1700

Data Index: 2309177 (Open Web Text)

Max Activating Token Index: 284

Text #3

Max Range: 3.2382. Min Range: -3.2382

Max Act: 3.0586. Min Act: -0.1700

Data Index: 3404493 (Open Web Text)

Max Activating Token Index: 361

Text #4

Max Range: 3.2382. Min Range: -3.2382

Max Act: 3.0992. Min Act: -0.1700

Data Index: 806035 (Open Web Text)

Max Activating Token Index: 276

Text #5

Max Range: 3.2382. Min Range: -3.2382

Max Act: 3.0466. Min Act: -0.1700

Data Index: 5952996 (Open Web Text)

Max Activating Token Index: 378

Text #6

Max Range: 3.2382. Min Range: -3.2382

Max Act: 3.0521. Min Act: -0.1700

Data Index: 2327420 (Open Web Text)

Max Activating Token Index: 521

Text #7

Max Range: 3.2382. Min Range: -3.2382

Max Act: 3.0462. Min Act: -0.1700

Data Index: 7367506 (Open Web Text)

Max Activating Token Index: 238

Text #8

Max Range: 3.2382. Min Range: -3.2382

Max Act: 3.0300. Min Act: -0.1700

Data Index: 5640440 (Open Web Text)

Max Activating Token Index: 450

Text #9

Max Range: 3.2382. Min Range: -3.2382

Max Act: 3.0298. Min Act: -0.1700

Data Index: 6942033 (Open Web Text)

Max Activating Token Index: 180

Text #10

Max Range: 3.2382. Min Range: -3.2382

Max Act: 3.0339. Min Act: -0.1700

Data Index: 3574041 (Open Web Text)

Max Activating Token Index: 44

Text #11

Max Range: 3.2382. Min Range: -3.2382

Max Act: 3.0266. Min Act: -0.1700

Data Index: 8639395 (Open Web Text)

Max Activating Token Index: 740

Text #12

Max Range: 3.2382. Min Range: -3.2382

Max Act: 2.9977. Min Act: -0.1700

Data Index: 6134199 (Open Web Text)

Max Activating Token Index: 888

Text #13

Max Range: 3.2382. Min Range: -3.2382

Max Act: 3.0156. Min Act: -0.1700

Data Index: 7626840 (Open Web Text)

Max Activating Token Index: 834

Text #14

Max Range: 3.2382. Min Range: -3.2382

Max Act: 3.0412. Min Act: -0.1700

Data Index: 2038239 (Open Web Text)

Max Activating Token Index: 29

Text #15

Max Range: 3.2382. Min Range: -3.2382

Max Act: 3.0273. Min Act: -0.1700

Data Index: 8488438 (Open Web Text)

Max Activating Token Index: 721

Text #16

Max Range: 3.2382. Min Range: -3.2382

Max Act: 3.0017. Min Act: -0.1700

Data Index: 875082 (Open Web Text)

Max Activating Token Index: 716

Text #17

Max Range: 3.2382. Min Range: -3.2382

Max Act: 3.0158. Min Act: -0.1700

Data Index: 1948654 (Open Web Text)

Max Activating Token Index: 536

Text #18

Max Range: 3.2382. Min Range: -3.2382

Max Act: 3.0060. Min Act: -0.1700

Data Index: 3415057 (Open Web Text)

Max Activating Token Index: 347

Text #19

Max Range: 3.2382. Min Range: -3.2382

Max Act: 3.0019. Min Act: -0.1700

Data Index: 3519608 (Open Web Text)

Max Activating Token Index: 527