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

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

Neuron 1981 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5969. Min Range: -0.5969

Max Act: 0.5969. Min Act: -0.0000

Data Index: 846141 (C4 (Web Text))

Max Activating Token Index: 665

Text #1

Max Range: 0.5969. Min Range: -0.5969

Max Act: 0.3637. Min Act: -0.0000

Data Index: 1319834 (C4 (Web Text))

Max Activating Token Index: 191

Text #2

Max Range: 0.5969. Min Range: -0.5969

Max Act: 0.3424. Min Act: -0.0000

Data Index: 1142690 (C4 (Web Text))

Max Activating Token Index: 778

Text #3

Max Range: 0.5969. Min Range: -0.5969

Max Act: 0.3541. Min Act: -0.0000

Data Index: 674987 (C4 (Web Text))

Max Activating Token Index: 154

Text #4

Max Range: 0.5969. Min Range: -0.5969

Max Act: 0.3532. Min Act: -0.0000

Data Index: 561897 (C4 (Web Text))

Max Activating Token Index: 599

Text #5

Max Range: 0.5969. Min Range: -0.5969

Max Act: 0.3230. Min Act: -0.0000

Data Index: 107486 (C4 (Web Text))

Max Activating Token Index: 710

Text #6

Max Range: 0.5969. Min Range: -0.5969

Max Act: 0.3451. Min Act: -0.0000

Data Index: 899565 (C4 (Web Text))

Max Activating Token Index: 385

Text #7

Max Range: 0.5969. Min Range: -0.5969

Max Act: 0.3225. Min Act: -0.0000

Data Index: 503136 (C4 (Web Text))

Max Activating Token Index: 38

Text #8

Max Range: 0.5969. Min Range: -0.5969

Max Act: 0.2838. Min Act: -0.0000

Data Index: 837488 (C4 (Web Text))

Max Activating Token Index: 849

Text #9

Max Range: 0.5969. Min Range: -0.5969

Max Act: 0.2840. Min Act: -0.0000

Data Index: 363846 (C4 (Web Text))

Max Activating Token Index: 605

Text #10

Max Range: 0.5969. Min Range: -0.5969

Max Act: 0.2840. Min Act: -0.0000

Data Index: 1342342 (C4 (Web Text))

Max Activating Token Index: 927

Text #11

Max Range: 0.5969. Min Range: -0.5969

Max Act: 0.2724. Min Act: -0.0000

Data Index: 452207 (C4 (Web Text))

Max Activating Token Index: 287

Text #12

Max Range: 0.5969. Min Range: -0.5969

Max Act: 0.2888. Min Act: -0.0000

Data Index: 1122905 (C4 (Web Text))

Max Activating Token Index: 673

Text #13

Max Range: 0.5969. Min Range: -0.5969

Max Act: 0.2507. Min Act: -0.0000

Data Index: 563495 (C4 (Web Text))

Max Activating Token Index: 211

Text #14

Max Range: 0.5969. Min Range: -0.5969

Max Act: 0.2575. Min Act: -0.0000

Data Index: 727471 (C4 (Web Text))

Max Activating Token Index: 633

Text #15

Max Range: 0.5969. Min Range: -0.5969

Max Act: 0.3186. Min Act: -0.0000

Data Index: 315888 (C4 (Web Text))

Max Activating Token Index: 935

Text #16

Max Range: 0.5969. Min Range: -0.5969

Max Act: 0.2678. Min Act: -0.0000

Data Index: 1056574 (C4 (Web Text))

Max Activating Token Index: 975

Text #17

Max Range: 0.5969. Min Range: -0.5969

Max Act: 0.2848. Min Act: -0.0000

Data Index: 1273257 (C4 (Web Text))

Max Activating Token Index: 991

Text #18

Max Range: 0.5969. Min Range: -0.5969

Max Act: 0.2566. Min Act: -0.0000

Data Index: 80916 (C4 (Web Text))

Max Activating Token Index: 274

Text #19

Max Range: 0.5969. Min Range: -0.5969

Max Act: 0.2647. Min Act: -0.0000

Data Index: 796600 (C4 (Web Text))

Max Activating Token Index: 205