Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1638 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3749. Min Range: -0.3749

Max Act: 0.3749. Min Act: -0.0000

Data Index: 99109 (C4 (Web Text))

Max Activating Token Index: 999

Text #1

Max Range: 0.3749. Min Range: -0.3749

Max Act: 0.3593. Min Act: -0.0000

Data Index: 938046 (C4 (Web Text))

Max Activating Token Index: 277

Text #2

Max Range: 0.3749. Min Range: -0.3749

Max Act: 0.3687. Min Act: -0.0000

Data Index: 690226 (C4 (Web Text))

Max Activating Token Index: 620

Text #3

Max Range: 0.3749. Min Range: -0.3749

Max Act: 0.3176. Min Act: -0.0001

Data Index: 1071278 (C4 (Web Text))

Max Activating Token Index: 252

Text #4

Max Range: 0.3749. Min Range: -0.3749

Max Act: 0.3255. Min Act: -0.0001

Data Index: 433766 (C4 (Web Text))

Max Activating Token Index: 765

Text #5

Max Range: 0.3749. Min Range: -0.3749

Max Act: 0.2983. Min Act: -0.0001

Data Index: 498800 (C4 (Web Text))

Max Activating Token Index: 74

Text #6

Max Range: 0.3749. Min Range: -0.3749

Max Act: 0.3040. Min Act: -0.0001

Data Index: 1157612 (C4 (Web Text))

Max Activating Token Index: 61

Text #7

Max Range: 0.3749. Min Range: -0.3749

Max Act: 0.2674. Min Act: -0.0001

Data Index: 742612 (C4 (Web Text))

Max Activating Token Index: 662

Text #8

Max Range: 0.3749. Min Range: -0.3749

Max Act: 0.2641. Min Act: -0.0001

Data Index: 696848 (C4 (Web Text))

Max Activating Token Index: 568

Text #9

Max Range: 0.3749. Min Range: -0.3749

Max Act: 0.2610. Min Act: -0.0001

Data Index: 119771 (C4 (Web Text))

Max Activating Token Index: 919

Text #10

Max Range: 0.3749. Min Range: -0.3749

Max Act: 0.2684. Min Act: -0.0001

Data Index: 97071 (C4 (Web Text))

Max Activating Token Index: 38

Text #11

Max Range: 0.3749. Min Range: -0.3749

Max Act: 0.2485. Min Act: -0.0001

Data Index: 1002193 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 0.3749. Min Range: -0.3749

Max Act: 0.2502. Min Act: -0.0001

Data Index: 96807 (C4 (Web Text))

Max Activating Token Index: 719

Text #13

Max Range: 0.3749. Min Range: -0.3749

Max Act: 0.2516. Min Act: -0.0001

Data Index: 198548 (C4 (Web Text))

Max Activating Token Index: 566

Text #14

Max Range: 0.3749. Min Range: -0.3749

Max Act: 0.2536. Min Act: -0.0001

Data Index: 395531 (C4 (Web Text))

Max Activating Token Index: 631

Text #15

Max Range: 0.3749. Min Range: -0.3749

Max Act: 0.2421. Min Act: -0.0000

Data Index: 317524 (C4 (Web Text))

Max Activating Token Index: 477

Text #16

Max Range: 0.3749. Min Range: -0.3749

Max Act: 0.2303. Min Act: -0.0000

Data Index: 498083 (C4 (Web Text))

Max Activating Token Index: 301

Text #17

Max Range: 0.3749. Min Range: -0.3749

Max Act: 0.2365. Min Act: -0.0001

Data Index: 491153 (C4 (Web Text))

Max Activating Token Index: 206

Text #18

Max Range: 0.3749. Min Range: -0.3749

Max Act: 0.2427. Min Act: -0.0001

Data Index: 149333 (C4 (Web Text))

Max Activating Token Index: 350

Text #19

Max Range: 0.3749. Min Range: -0.3749

Max Act: 0.2420. Min Act: -0.0000

Data Index: 719364 (C4 (Web Text))

Max Activating Token Index: 814