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

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

Neuron 1633 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: 2.0025. Min Range: -2.0025

Max Act: 2.0025. Min Act: -0.0001

Data Index: 1114789 (C4 (Web Text))

Max Activating Token Index: 818

Text #1

Max Range: 2.0025. Min Range: -2.0025

Max Act: 1.9330. Min Act: -0.0001

Data Index: 1296471 (C4 (Web Text))

Max Activating Token Index: 509

Text #2

Max Range: 2.0025. Min Range: -2.0025

Max Act: 1.9161. Min Act: -0.0001

Data Index: 1346185 (C4 (Web Text))

Max Activating Token Index: 223

Text #3

Max Range: 2.0025. Min Range: -2.0025

Max Act: 1.8402. Min Act: -0.0001

Data Index: 345515 (C4 (Web Text))

Max Activating Token Index: 367

Text #4

Max Range: 2.0025. Min Range: -2.0025

Max Act: 1.8178. Min Act: -0.0001

Data Index: 197520 (C4 (Web Text))

Max Activating Token Index: 707

Text #5

Max Range: 2.0025. Min Range: -2.0025

Max Act: 1.9989. Min Act: -0.0001

Data Index: 1201758 (C4 (Web Text))

Max Activating Token Index: 859

Text #6

Max Range: 2.0025. Min Range: -2.0025

Max Act: 1.8142. Min Act: -0.0001

Data Index: 375592 (C4 (Web Text))

Max Activating Token Index: 685

Text #7

Max Range: 2.0025. Min Range: -2.0025

Max Act: 1.7037. Min Act: -0.0001

Data Index: 194541 (C4 (Web Text))

Max Activating Token Index: 102

Text #8

Max Range: 2.0025. Min Range: -2.0025

Max Act: 1.7070. Min Act: -0.0001

Data Index: 1295391 (C4 (Web Text))

Max Activating Token Index: 88

Text #9

Max Range: 2.0025. Min Range: -2.0025

Max Act: 1.1406. Min Act: -0.0000

Data Index: 578657 (C4 (Web Text))

Max Activating Token Index: 867

Text #10

Max Range: 2.0025. Min Range: -2.0025

Max Act: 1.1042. Min Act: -0.0000

Data Index: 842030 (C4 (Web Text))

Max Activating Token Index: 45

Text #11

Max Range: 2.0025. Min Range: -2.0025

Max Act: 1.0869. Min Act: -0.0000

Data Index: 541275 (C4 (Web Text))

Max Activating Token Index: 28

Text #12

Max Range: 2.0025. Min Range: -2.0025

Max Act: 1.0763. Min Act: -0.0000

Data Index: 686207 (C4 (Web Text))

Max Activating Token Index: 32

Text #13

Max Range: 2.0025. Min Range: -2.0025

Max Act: 1.0174. Min Act: -0.0001

Data Index: 1209957 (C4 (Web Text))

Max Activating Token Index: 9

Text #14

Max Range: 2.0025. Min Range: -2.0025

Max Act: 0.9818. Min Act: -0.0000

Data Index: 172630 (C4 (Web Text))

Max Activating Token Index: 384

Text #15

Max Range: 2.0025. Min Range: -2.0025

Max Act: 0.9608. Min Act: -0.0000

Data Index: 457419 (C4 (Web Text))

Max Activating Token Index: 241

Text #16

Max Range: 2.0025. Min Range: -2.0025

Max Act: 0.9669. Min Act: -0.0000

Data Index: 542409 (C4 (Web Text))

Max Activating Token Index: 416

Text #17

Max Range: 2.0025. Min Range: -2.0025

Max Act: 0.9352. Min Act: -0.0000

Data Index: 334247 (C4 (Web Text))

Max Activating Token Index: 684

Text #18

Max Range: 2.0025. Min Range: -2.0025

Max Act: 0.8838. Min Act: -0.0000

Data Index: 1273035 (C4 (Web Text))

Max Activating Token Index: 454

Text #19

Max Range: 2.0025. Min Range: -2.0025

Max Act: 0.9840. Min Act: -0.0000

Data Index: 345424 (C4 (Web Text))

Max Activating Token Index: 133