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

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

Neuron 5658 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: 4.3235. Min Range: -4.3235

Max Act: 4.3235. Min Act: -0.0000

Data Index: 400082 (C4 (Web Text))

Max Activating Token Index: 467

Text #1

Max Range: 4.3235. Min Range: -4.3235

Max Act: 4.0282. Min Act: -0.0001

Data Index: 1134283 (C4 (Web Text))

Max Activating Token Index: 613

Text #2

Max Range: 4.3235. Min Range: -4.3235

Max Act: 3.9270. Min Act: -0.0000

Data Index: 23774 (C4 (Web Text))

Max Activating Token Index: 468

Text #3

Max Range: 4.3235. Min Range: -4.3235

Max Act: 3.7387. Min Act: -0.0000

Data Index: 650495 (C4 (Web Text))

Max Activating Token Index: 500

Text #4

Max Range: 4.3235. Min Range: -4.3235

Max Act: 3.7909. Min Act: -0.0000

Data Index: 365030 (C4 (Web Text))

Max Activating Token Index: 990

Text #5

Max Range: 4.3235. Min Range: -4.3235

Max Act: 3.5658. Min Act: -0.0000

Data Index: 631257 (C4 (Web Text))

Max Activating Token Index: 344

Text #6

Max Range: 4.3235. Min Range: -4.3235

Max Act: 3.3671. Min Act: -0.0001

Data Index: 236982 (C4 (Web Text))

Max Activating Token Index: 489

Text #7

Max Range: 4.3235. Min Range: -4.3235

Max Act: 3.4728. Min Act: -0.0000

Data Index: 1055579 (C4 (Web Text))

Max Activating Token Index: 204

Text #8

Max Range: 4.3235. Min Range: -4.3235

Max Act: 3.5080. Min Act: -0.0000

Data Index: 1219711 (C4 (Web Text))

Max Activating Token Index: 557

Text #9

Max Range: 4.3235. Min Range: -4.3235

Max Act: 3.3361. Min Act: -0.0000

Data Index: 367116 (C4 (Web Text))

Max Activating Token Index: 114

Text #10

Max Range: 4.3235. Min Range: -4.3235

Max Act: 3.3943. Min Act: -0.0000

Data Index: 688945 (C4 (Web Text))

Max Activating Token Index: 258

Text #11

Max Range: 4.3235. Min Range: -4.3235

Max Act: 3.5821. Min Act: -0.0000

Data Index: 1161539 (C4 (Web Text))

Max Activating Token Index: 767

Text #12

Max Range: 4.3235. Min Range: -4.3235

Max Act: 3.4088. Min Act: -0.0000

Data Index: 845720 (C4 (Web Text))

Max Activating Token Index: 240

Text #13

Max Range: 4.3235. Min Range: -4.3235

Max Act: 3.1972. Min Act: -0.0000

Data Index: 120256 (C4 (Web Text))

Max Activating Token Index: 1019

Text #14

Max Range: 4.3235. Min Range: -4.3235

Max Act: 3.0696. Min Act: -0.0000

Data Index: 801290 (C4 (Web Text))

Max Activating Token Index: 738

Text #15

Max Range: 4.3235. Min Range: -4.3235

Max Act: 3.3363. Min Act: -0.0001

Data Index: 1257533 (C4 (Web Text))

Max Activating Token Index: 885

Text #16

Max Range: 4.3235. Min Range: -4.3235

Max Act: 3.3268. Min Act: -0.0001

Data Index: 297261 (C4 (Web Text))

Max Activating Token Index: 653

Text #17

Max Range: 4.3235. Min Range: -4.3235

Max Act: 3.1614. Min Act: -0.0000

Data Index: 582206 (C4 (Web Text))

Max Activating Token Index: 41

Text #18

Max Range: 4.3235. Min Range: -4.3235

Max Act: 3.1572. Min Act: -0.0001

Data Index: 702279 (C4 (Web Text))

Max Activating Token Index: 128

Text #19

Max Range: 4.3235. Min Range: -4.3235

Max Act: 3.1588. Min Act: -0.0000

Data Index: 764475 (C4 (Web Text))

Max Activating Token Index: 606