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

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

Neuron 1505 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.4427. Min Act: -0.0000

Data Index: 864244 (C4 (Web Text))

Max Activating Token Index: 838

Text #1

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.3747. Min Act: -0.0000

Data Index: 813652 (C4 (Web Text))

Max Activating Token Index: 72

Text #2

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.3557. Min Act: -0.0000

Data Index: 1325556 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.3527. Min Act: -0.0000

Data Index: 1356778 (C4 (Web Text))

Max Activating Token Index: 840

Text #4

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.3544. Min Act: -0.0000

Data Index: 907103 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.3634. Min Act: -0.0000

Data Index: 1278070 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.3368. Min Act: -0.0000

Data Index: 817431 (C4 (Web Text))

Max Activating Token Index: 656

Text #7

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.3239. Min Act: -0.0000

Data Index: 342443 (C4 (Web Text))

Max Activating Token Index: 693

Text #8

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.3245. Min Act: -0.0000

Data Index: 417850 (C4 (Web Text))

Max Activating Token Index: 686

Text #9

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.3148. Min Act: -0.0000

Data Index: 119267 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.3198. Min Act: -0.0000

Data Index: 1209570 (C4 (Web Text))

Max Activating Token Index: 536

Text #11

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.3105. Min Act: -0.0000

Data Index: 133047 (C4 (Web Text))

Max Activating Token Index: 251

Text #12

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.3197. Min Act: -0.0000

Data Index: 889459 (C4 (Web Text))

Max Activating Token Index: 710

Text #13

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.3170. Min Act: -0.0000

Data Index: 967647 (C4 (Web Text))

Max Activating Token Index: 842

Text #14

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.2927. Min Act: -0.0000

Data Index: 561260 (C4 (Web Text))

Max Activating Token Index: 563

Text #15

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.3039. Min Act: -0.0000

Data Index: 397969 (C4 (Web Text))

Max Activating Token Index: 838

Text #16

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.2945. Min Act: -0.0000

Data Index: 637470 (C4 (Web Text))

Max Activating Token Index: 61

Text #17

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.2658. Min Act: -0.0000

Data Index: 1272194 (C4 (Web Text))

Max Activating Token Index: 907

Text #18

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.3061. Min Act: -0.0000

Data Index: 855802 (C4 (Web Text))

Max Activating Token Index: 400

Text #19

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.2865. Min Act: -0.0000

Data Index: 1144241 (C4 (Web Text))

Max Activating Token Index: 937