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

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

Neuron 215 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4231. Min Range: -0.4231

Max Act: 0.4231. Min Act: -0.0001

Data Index: 123181 (C4 (Web Text))

Max Activating Token Index: 444

Text #1

Max Range: 0.4231. Min Range: -0.4231

Max Act: 0.3556. Min Act: -0.0001

Data Index: 461056 (C4 (Web Text))

Max Activating Token Index: 293

Text #2

Max Range: 0.4231. Min Range: -0.4231

Max Act: 0.0670. Min Act: -0.0001

Data Index: 1214737 (C4 (Web Text))

Max Activating Token Index: 730

Text #3

Max Range: 0.4231. Min Range: -0.4231

Max Act: 0.0788. Min Act: -0.0001

Data Index: 756103 (C4 (Web Text))

Max Activating Token Index: 84

Text #4

Max Range: 0.4231. Min Range: -0.4231

Max Act: 0.0720. Min Act: -0.0001

Data Index: 45343 (C4 (Web Text))

Max Activating Token Index: 813

Text #5

Max Range: 0.4231. Min Range: -0.4231

Max Act: 0.0732. Min Act: -0.0001

Data Index: 957451 (C4 (Web Text))

Max Activating Token Index: 56

Text #6

Max Range: 0.4231. Min Range: -0.4231

Max Act: 0.0586. Min Act: -0.0000

Data Index: 1009294 (C4 (Web Text))

Max Activating Token Index: 384

Text #7

Max Range: 0.4231. Min Range: -0.4231

Max Act: 0.0551. Min Act: -0.0001

Data Index: 158116 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 0.4231. Min Range: -0.4231

Max Act: 0.0472. Min Act: -0.0001

Data Index: 603089 (C4 (Web Text))

Max Activating Token Index: 189

Text #9

Max Range: 0.4231. Min Range: -0.4231

Max Act: 0.0520. Min Act: -0.0001

Data Index: 361504 (C4 (Web Text))

Max Activating Token Index: 590

Text #10

Max Range: 0.4231. Min Range: -0.4231

Max Act: 0.0546. Min Act: -0.0001

Data Index: 1320134 (C4 (Web Text))

Max Activating Token Index: 466

Text #11

Max Range: 0.4231. Min Range: -0.4231

Max Act: 0.0480. Min Act: -0.0001

Data Index: 381025 (C4 (Web Text))

Max Activating Token Index: 234

Text #12

Max Range: 0.4231. Min Range: -0.4231

Max Act: 0.0511. Min Act: -0.0001

Data Index: 328250 (C4 (Web Text))

Max Activating Token Index: 810

Text #13

Max Range: 0.4231. Min Range: -0.4231

Max Act: 0.0492. Min Act: -0.0001

Data Index: 1011684 (C4 (Web Text))

Max Activating Token Index: 994

Text #14

Max Range: 0.4231. Min Range: -0.4231

Max Act: 0.0526. Min Act: -0.0001

Data Index: 431715 (C4 (Web Text))

Max Activating Token Index: 77

Text #15

Max Range: 0.4231. Min Range: -0.4231

Max Act: 0.0482. Min Act: -0.0001

Data Index: 176745 (C4 (Web Text))

Max Activating Token Index: 11

Text #16

Max Range: 0.4231. Min Range: -0.4231

Max Act: 0.0413. Min Act: -0.0001

Data Index: 1235861 (C4 (Web Text))

Max Activating Token Index: 723

Text #17

Max Range: 0.4231. Min Range: -0.4231

Max Act: 0.0522. Min Act: -0.0001

Data Index: 218148 (C4 (Web Text))

Max Activating Token Index: 505

Text #18

Max Range: 0.4231. Min Range: -0.4231

Max Act: 0.0428. Min Act: -0.0001

Data Index: 108878 (C4 (Web Text))

Max Activating Token Index: 650

Text #19

Max Range: 0.4231. Min Range: -0.4231

Max Act: 0.0450. Min Act: -0.0001

Data Index: 274939 (C4 (Web Text))

Max Activating Token Index: 22