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

Dataset: Open Web Text

Neuron 659 in Layer 3

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: 4.3365. Min Range: -4.3365

Max Act: 4.3365. Min Act: -0.1700

Data Index: 8794378 (Open Web Text)

Max Activating Token Index: 814

Text #1

Max Range: 4.3365. Min Range: -4.3365

Max Act: 4.3310. Min Act: -0.1700

Data Index: 898830 (Open Web Text)

Max Activating Token Index: 28

Text #2

Max Range: 4.3365. Min Range: -4.3365

Max Act: 4.2506. Min Act: -0.1700

Data Index: 380057 (Open Web Text)

Max Activating Token Index: 518

Text #3

Max Range: 4.3365. Min Range: -4.3365

Max Act: 4.3094. Min Act: -0.1700

Data Index: 4479395 (Open Web Text)

Max Activating Token Index: 224

Text #4

Max Range: 4.3365. Min Range: -4.3365

Max Act: 4.1570. Min Act: -0.1700

Data Index: 2592769 (Open Web Text)

Max Activating Token Index: 501

Text #5

Max Range: 4.3365. Min Range: -4.3365

Max Act: 4.1670. Min Act: -0.1700

Data Index: 7901547 (Open Web Text)

Max Activating Token Index: 629

Text #6

Max Range: 4.3365. Min Range: -4.3365

Max Act: 4.1678. Min Act: -0.1700

Data Index: 457113 (Open Web Text)

Max Activating Token Index: 270

Text #7

Max Range: 4.3365. Min Range: -4.3365

Max Act: 4.1692. Min Act: -0.1700

Data Index: 1294813 (Open Web Text)

Max Activating Token Index: 965

Text #8

Max Range: 4.3365. Min Range: -4.3365

Max Act: 4.1384. Min Act: -0.1700

Data Index: 5665257 (Open Web Text)

Max Activating Token Index: 767

Text #9

Max Range: 4.3365. Min Range: -4.3365

Max Act: 4.1412. Min Act: -0.1700

Data Index: 4068206 (Open Web Text)

Max Activating Token Index: 282

Text #10

Max Range: 4.3365. Min Range: -4.3365

Max Act: 4.0868. Min Act: -0.1700

Data Index: 5829903 (Open Web Text)

Max Activating Token Index: 423

Text #11

Max Range: 4.3365. Min Range: -4.3365

Max Act: 4.1104. Min Act: -0.1700

Data Index: 2212561 (Open Web Text)

Max Activating Token Index: 394

Text #12

Max Range: 4.3365. Min Range: -4.3365

Max Act: 4.1309. Min Act: -0.1700

Data Index: 4766178 (Open Web Text)

Max Activating Token Index: 353

Text #13

Max Range: 4.3365. Min Range: -4.3365

Max Act: 4.1247. Min Act: -0.1700

Data Index: 4006679 (Open Web Text)

Max Activating Token Index: 832

Text #14

Max Range: 4.3365. Min Range: -4.3365

Max Act: 4.1173. Min Act: -0.1700

Data Index: 8476095 (Open Web Text)

Max Activating Token Index: 62

Text #15

Max Range: 4.3365. Min Range: -4.3365

Max Act: 4.1112. Min Act: -0.1700

Data Index: 7488535 (Open Web Text)

Max Activating Token Index: 355

Text #16

Max Range: 4.3365. Min Range: -4.3365

Max Act: 4.1184. Min Act: -0.1700

Data Index: 4615260 (Open Web Text)

Max Activating Token Index: 948

Text #17

Max Range: 4.3365. Min Range: -4.3365

Max Act: 4.0864. Min Act: -0.1700

Data Index: 2318839 (Open Web Text)

Max Activating Token Index: 60

Text #18

Max Range: 4.3365. Min Range: -4.3365

Max Act: 4.0896. Min Act: -0.1700

Data Index: 6869427 (Open Web Text)

Max Activating Token Index: 587

Text #19

Max Range: 4.3365. Min Range: -4.3365

Max Act: 4.0820. Min Act: -0.1700

Data Index: 7310619 (Open Web Text)

Max Activating Token Index: 29