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

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

Neuron 2696 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8515. Min Range: -2.8515

Max Act: 2.8515. Min Act: -0.0000

Data Index: 658829 (C4 (Web Text))

Max Activating Token Index: 999

Text #1

Max Range: 2.8515. Min Range: -2.8515

Max Act: 2.3605. Min Act: -0.0000

Data Index: 378735 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 2.8515. Min Range: -2.8515

Max Act: 2.1798. Min Act: -0.0000

Data Index: 973346 (C4 (Web Text))

Max Activating Token Index: 200

Text #3

Max Range: 2.8515. Min Range: -2.8515

Max Act: 2.2123. Min Act: -0.0000

Data Index: 370765 (C4 (Web Text))

Max Activating Token Index: 205

Text #4

Max Range: 2.8515. Min Range: -2.8515

Max Act: 2.2015. Min Act: -0.0000

Data Index: 1325470 (C4 (Web Text))

Max Activating Token Index: 686

Text #5

Max Range: 2.8515. Min Range: -2.8515

Max Act: 2.2587. Min Act: -0.0000

Data Index: 1265777 (C4 (Web Text))

Max Activating Token Index: 575

Text #6

Max Range: 2.8515. Min Range: -2.8515

Max Act: 1.8851. Min Act: -0.0000

Data Index: 746069 (C4 (Web Text))

Max Activating Token Index: 414

Text #7

Max Range: 2.8515. Min Range: -2.8515

Max Act: 1.8849. Min Act: -0.0000

Data Index: 1268945 (C4 (Web Text))

Max Activating Token Index: 709

Text #8

Max Range: 2.8515. Min Range: -2.8515

Max Act: 1.9740. Min Act: -0.0000

Data Index: 576733 (C4 (Web Text))

Max Activating Token Index: 410

Text #9

Max Range: 2.8515. Min Range: -2.8515

Max Act: 1.8554. Min Act: -0.0000

Data Index: 140691 (C4 (Web Text))

Max Activating Token Index: 664

Text #10

Max Range: 2.8515. Min Range: -2.8515

Max Act: 2.0552. Min Act: -0.0000

Data Index: 1056682 (C4 (Web Text))

Max Activating Token Index: 867

Text #11

Max Range: 2.8515. Min Range: -2.8515

Max Act: 1.8920. Min Act: -0.0000

Data Index: 607270 (C4 (Web Text))

Max Activating Token Index: 726

Text #12

Max Range: 2.8515. Min Range: -2.8515

Max Act: 1.9747. Min Act: -0.0001

Data Index: 628242 (C4 (Web Text))

Max Activating Token Index: 418

Text #13

Max Range: 2.8515. Min Range: -2.8515

Max Act: 1.7073. Min Act: -0.0000

Data Index: 825053 (C4 (Web Text))

Max Activating Token Index: 1009

Text #14

Max Range: 2.8515. Min Range: -2.8515

Max Act: 1.7103. Min Act: -0.0000

Data Index: 1334076 (C4 (Web Text))

Max Activating Token Index: 879

Text #15

Max Range: 2.8515. Min Range: -2.8515

Max Act: 1.7936. Min Act: -0.0000

Data Index: 808618 (C4 (Web Text))

Max Activating Token Index: 328

Text #16

Max Range: 2.8515. Min Range: -2.8515

Max Act: 1.5979. Min Act: -0.0000

Data Index: 732397 (C4 (Web Text))

Max Activating Token Index: 725

Text #17

Max Range: 2.8515. Min Range: -2.8515

Max Act: 1.6379. Min Act: -0.0000

Data Index: 76566 (C4 (Web Text))

Max Activating Token Index: 745

Text #18

Max Range: 2.8515. Min Range: -2.8515

Max Act: 1.6322. Min Act: -0.0000

Data Index: 1260618 (C4 (Web Text))

Max Activating Token Index: 565

Text #19

Max Range: 2.8515. Min Range: -2.8515

Max Act: 1.7791. Min Act: -0.0000

Data Index: 271084 (C4 (Web Text))

Max Activating Token Index: 864