Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 1383 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.7174. Min Range: -3.7174

Max Act: 3.7174. Min Act: -0.0000

Data Index: 852243 (The Pile)

Max Activating Token Index: 453

Text #1

Max Range: 3.7174. Min Range: -3.7174

Max Act: 3.3389. Min Act: -0.0000

Data Index: 246111 (The Pile)

Max Activating Token Index: 560

Text #2

Max Range: 3.7174. Min Range: -3.7174

Max Act: 3.1311. Min Act: -0.0000

Data Index: 262292 (The Pile)

Max Activating Token Index: 526

Text #3

Max Range: 3.7174. Min Range: -3.7174

Max Act: 3.2404. Min Act: -0.0000

Data Index: 470660 (The Pile)

Max Activating Token Index: 206

Text #4

Max Range: 3.7174. Min Range: -3.7174

Max Act: 3.0713. Min Act: -0.0000

Data Index: 968983 (The Pile)

Max Activating Token Index: 234

Text #5

Max Range: 3.7174. Min Range: -3.7174

Max Act: 3.4766. Min Act: -0.0000

Data Index: 1149122 (The Pile)

Max Activating Token Index: 62

Text #6

Max Range: 3.7174. Min Range: -3.7174

Max Act: 3.1550. Min Act: -0.0000

Data Index: 1287024 (The Pile)

Max Activating Token Index: 1007

Text #7

Max Range: 3.7174. Min Range: -3.7174

Max Act: 3.2736. Min Act: -0.0000

Data Index: 929252 (The Pile)

Max Activating Token Index: 452

Text #8

Max Range: 3.7174. Min Range: -3.7174

Max Act: 2.8271. Min Act: -0.0000

Data Index: 1127786 (The Pile)

Max Activating Token Index: 279

Text #9

Max Range: 3.7174. Min Range: -3.7174

Max Act: 3.5545. Min Act: -0.0000

Data Index: 1050438 (The Pile)

Max Activating Token Index: 306

Text #10

Max Range: 3.7174. Min Range: -3.7174

Max Act: 3.2265. Min Act: -0.0000

Data Index: 307992 (The Pile)

Max Activating Token Index: 173

Text #11

Max Range: 3.7174. Min Range: -3.7174

Max Act: 3.1314. Min Act: -0.0000

Data Index: 283584 (The Pile)

Max Activating Token Index: 605

Text #12

Max Range: 3.7174. Min Range: -3.7174

Max Act: 3.2407. Min Act: -0.0000

Data Index: 304004 (The Pile)

Max Activating Token Index: 307

Text #13

Max Range: 3.7174. Min Range: -3.7174

Max Act: 3.0469. Min Act: -0.0000

Data Index: 5545 (The Pile)

Max Activating Token Index: 403

Text #14

Max Range: 3.7174. Min Range: -3.7174

Max Act: 3.0696. Min Act: -0.0000

Data Index: 791030 (The Pile)

Max Activating Token Index: 457

Text #15

Max Range: 3.7174. Min Range: -3.7174

Max Act: 3.0039. Min Act: -0.0000

Data Index: 1976928 (The Pile)

Max Activating Token Index: 428

Text #16

Max Range: 3.7174. Min Range: -3.7174

Max Act: 2.4515. Min Act: -0.0000

Data Index: 23180 (The Pile)

Max Activating Token Index: 551

Text #17

Max Range: 3.7174. Min Range: -3.7174

Max Act: 3.0138. Min Act: -0.0000

Data Index: 280425 (The Pile)

Max Activating Token Index: 182

Text #18

Max Range: 3.7174. Min Range: -3.7174

Max Act: 2.8519. Min Act: -0.0000

Data Index: 1447495 (The Pile)

Max Activating Token Index: 611

Text #19

Max Range: 3.7174. Min Range: -3.7174

Max Act: 2.9826. Min Act: -0.0000

Data Index: 1264891 (The Pile)

Max Activating Token Index: 360