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

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

Neuron 4678 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.4028. Min Act: -0.0000

Data Index: 590649 (C4 (Web Text))

Max Activating Token Index: 295

Text #1

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.3657. Min Act: -0.0000

Data Index: 607983 (C4 (Web Text))

Max Activating Token Index: 175

Text #2

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.3135. Min Act: -0.0000

Data Index: 92301 (C4 (Web Text))

Max Activating Token Index: 487

Text #3

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.3154. Min Act: -0.0000

Data Index: 613215 (C4 (Web Text))

Max Activating Token Index: 862

Text #4

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.3348. Min Act: -0.0000

Data Index: 568062 (C4 (Web Text))

Max Activating Token Index: 329

Text #5

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.3205. Min Act: -0.0000

Data Index: 601607 (C4 (Web Text))

Max Activating Token Index: 756

Text #6

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.2775. Min Act: -0.0000

Data Index: 506153 (C4 (Web Text))

Max Activating Token Index: 572

Text #7

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.2880. Min Act: -0.0000

Data Index: 755514 (C4 (Web Text))

Max Activating Token Index: 683

Text #8

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.2614. Min Act: -0.0000

Data Index: 592653 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.2782. Min Act: -0.0000

Data Index: 63097 (C4 (Web Text))

Max Activating Token Index: 802

Text #10

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.2746. Min Act: -0.0000

Data Index: 412282 (C4 (Web Text))

Max Activating Token Index: 752

Text #11

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.2622. Min Act: -0.0000

Data Index: 330986 (C4 (Web Text))

Max Activating Token Index: 351

Text #12

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.2613. Min Act: -0.0000

Data Index: 1060239 (C4 (Web Text))

Max Activating Token Index: 430

Text #13

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.2431. Min Act: -0.0000

Data Index: 65638 (C4 (Web Text))

Max Activating Token Index: 25

Text #14

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.2534. Min Act: -0.0000

Data Index: 181792 (C4 (Web Text))

Max Activating Token Index: 961

Text #15

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.2542. Min Act: -0.0000

Data Index: 183183 (C4 (Web Text))

Max Activating Token Index: 427

Text #16

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.2432. Min Act: -0.0000

Data Index: 1219875 (C4 (Web Text))

Max Activating Token Index: 399

Text #17

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.2426. Min Act: -0.0000

Data Index: 1258746 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.2553. Min Act: -0.0000

Data Index: 53543 (C4 (Web Text))

Max Activating Token Index: 987

Text #19

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.2536. Min Act: -0.0000

Data Index: 676078 (C4 (Web Text))

Max Activating Token Index: 770