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

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

Neuron 635 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: 0.4254. Min Range: -0.4254

Max Act: 0.4254. Min Act: -0.0000

Data Index: 1171833 (C4 (Web Text))

Max Activating Token Index: 454

Text #1

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.3700. Min Act: -0.0001

Data Index: 186256 (C4 (Web Text))

Max Activating Token Index: 676

Text #2

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.3567. Min Act: -0.0001

Data Index: 1059036 (C4 (Web Text))

Max Activating Token Index: 381

Text #3

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.3024. Min Act: -0.0000

Data Index: 361959 (C4 (Web Text))

Max Activating Token Index: 232

Text #4

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.3127. Min Act: -0.0001

Data Index: 766202 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.3118. Min Act: -0.0001

Data Index: 651451 (C4 (Web Text))

Max Activating Token Index: 638

Text #6

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.3069. Min Act: -0.0001

Data Index: 217482 (C4 (Web Text))

Max Activating Token Index: 774

Text #7

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.3239. Min Act: -0.0000

Data Index: 141617 (C4 (Web Text))

Max Activating Token Index: 489

Text #8

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.3077. Min Act: -0.0000

Data Index: 334519 (C4 (Web Text))

Max Activating Token Index: 436

Text #9

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.2930. Min Act: -0.0000

Data Index: 20135 (C4 (Web Text))

Max Activating Token Index: 426

Text #10

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.3069. Min Act: -0.0000

Data Index: 69436 (C4 (Web Text))

Max Activating Token Index: 114

Text #11

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.2710. Min Act: -0.0001

Data Index: 247917 (C4 (Web Text))

Max Activating Token Index: 340

Text #12

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.2697. Min Act: -0.0001

Data Index: 317176 (C4 (Web Text))

Max Activating Token Index: 986

Text #13

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.2675. Min Act: -0.0000

Data Index: 1207608 (C4 (Web Text))

Max Activating Token Index: 98

Text #14

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.2739. Min Act: -0.0000

Data Index: 784697 (C4 (Web Text))

Max Activating Token Index: 811

Text #15

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.2693. Min Act: -0.0001

Data Index: 242968 (C4 (Web Text))

Max Activating Token Index: 1000

Text #16

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.2549. Min Act: -0.0000

Data Index: 102912 (C4 (Web Text))

Max Activating Token Index: 779

Text #17

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.2616. Min Act: -0.0001

Data Index: 1203978 (C4 (Web Text))

Max Activating Token Index: 886

Text #18

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.2511. Min Act: -0.0001

Data Index: 510329 (C4 (Web Text))

Max Activating Token Index: 170

Text #19

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.2480. Min Act: -0.0000

Data Index: 862797 (C4 (Web Text))

Max Activating Token Index: 250