Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1575 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5441. Min Range: -1.5441

Max Act: 1.5441. Min Act: -0.0000

Data Index: 1193519 (C4 (Web Text))

Max Activating Token Index: 890

Text #1

Max Range: 1.5441. Min Range: -1.5441

Max Act: 1.4437. Min Act: -0.0000

Data Index: 372110 (C4 (Web Text))

Max Activating Token Index: 482

Text #2

Max Range: 1.5441. Min Range: -1.5441

Max Act: 1.3441. Min Act: -0.0000

Data Index: 945087 (C4 (Web Text))

Max Activating Token Index: 739

Text #3

Max Range: 1.5441. Min Range: -1.5441

Max Act: 1.1971. Min Act: -0.0000

Data Index: 907538 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 1.5441. Min Range: -1.5441

Max Act: 1.1071. Min Act: -0.0000

Data Index: 492318 (C4 (Web Text))

Max Activating Token Index: 665

Text #5

Max Range: 1.5441. Min Range: -1.5441

Max Act: 1.1242. Min Act: -0.0000

Data Index: 160986 (C4 (Web Text))

Max Activating Token Index: 452

Text #6

Max Range: 1.5441. Min Range: -1.5441

Max Act: 1.1541. Min Act: -0.0000

Data Index: 955771 (C4 (Web Text))

Max Activating Token Index: 715

Text #7

Max Range: 1.5441. Min Range: -1.5441

Max Act: 1.1350. Min Act: -0.0000

Data Index: 791671 (C4 (Web Text))

Max Activating Token Index: 190

Text #8

Max Range: 1.5441. Min Range: -1.5441

Max Act: 1.0613. Min Act: -0.0000

Data Index: 349962 (C4 (Web Text))

Max Activating Token Index: 775

Text #9

Max Range: 1.5441. Min Range: -1.5441

Max Act: 1.1537. Min Act: -0.0000

Data Index: 1220109 (C4 (Web Text))

Max Activating Token Index: 913

Text #10

Max Range: 1.5441. Min Range: -1.5441

Max Act: 1.0846. Min Act: -0.0000

Data Index: 133373 (C4 (Web Text))

Max Activating Token Index: 687

Text #11

Max Range: 1.5441. Min Range: -1.5441

Max Act: 1.0436. Min Act: -0.0000

Data Index: 431704 (C4 (Web Text))

Max Activating Token Index: 34

Text #12

Max Range: 1.5441. Min Range: -1.5441

Max Act: 1.0408. Min Act: -0.0000

Data Index: 631087 (C4 (Web Text))

Max Activating Token Index: 318

Text #13

Max Range: 1.5441. Min Range: -1.5441

Max Act: 1.1196. Min Act: -0.0000

Data Index: 881042 (C4 (Web Text))

Max Activating Token Index: 311

Text #14

Max Range: 1.5441. Min Range: -1.5441

Max Act: 1.0858. Min Act: -0.0000

Data Index: 408338 (C4 (Web Text))

Max Activating Token Index: 468

Text #15

Max Range: 1.5441. Min Range: -1.5441

Max Act: 1.0485. Min Act: -0.0000

Data Index: 889577 (C4 (Web Text))

Max Activating Token Index: 107

Text #16

Max Range: 1.5441. Min Range: -1.5441

Max Act: 1.0342. Min Act: -0.0000

Data Index: 306113 (C4 (Web Text))

Max Activating Token Index: 537

Text #17

Max Range: 1.5441. Min Range: -1.5441

Max Act: 1.0246. Min Act: -0.0000

Data Index: 929749 (C4 (Web Text))

Max Activating Token Index: 231

Text #18

Max Range: 1.5441. Min Range: -1.5441

Max Act: 1.0133. Min Act: -0.0000

Data Index: 1157331 (C4 (Web Text))

Max Activating Token Index: 433

Text #19

Max Range: 1.5441. Min Range: -1.5441

Max Act: 1.0098. Min Act: -0.0000

Data Index: 391376 (C4 (Web Text))

Max Activating Token Index: 109