Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1612 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2592. Min Range: -1.2592

Max Act: 1.2592. Min Act: -0.0000

Data Index: 1302588 (C4 (Web Text))

Max Activating Token Index: 288

Text #1

Max Range: 1.2592. Min Range: -1.2592

Max Act: 1.2539. Min Act: -0.0001

Data Index: 970036 (C4 (Web Text))

Max Activating Token Index: 340

Text #2

Max Range: 1.2592. Min Range: -1.2592

Max Act: 1.2536. Min Act: -0.0000

Data Index: 880158 (C4 (Web Text))

Max Activating Token Index: 684

Text #3

Max Range: 1.2592. Min Range: -1.2592

Max Act: 1.1610. Min Act: -0.0001

Data Index: 606006 (C4 (Web Text))

Max Activating Token Index: 946

Text #4

Max Range: 1.2592. Min Range: -1.2592

Max Act: 1.1789. Min Act: -0.0000

Data Index: 737330 (C4 (Web Text))

Max Activating Token Index: 193

Text #5

Max Range: 1.2592. Min Range: -1.2592

Max Act: 1.1700. Min Act: -0.0001

Data Index: 126208 (C4 (Web Text))

Max Activating Token Index: 219

Text #6

Max Range: 1.2592. Min Range: -1.2592

Max Act: 1.1679. Min Act: -0.0001

Data Index: 598710 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 1.2592. Min Range: -1.2592

Max Act: 1.1554. Min Act: -0.0001

Data Index: 1367713 (Python Code)

Max Activating Token Index: 174

Text #8

Max Range: 1.2592. Min Range: -1.2592

Max Act: 1.1967. Min Act: -0.0000

Data Index: 800744 (C4 (Web Text))

Max Activating Token Index: 910

Text #9

Max Range: 1.2592. Min Range: -1.2592

Max Act: 1.1485. Min Act: -0.0001

Data Index: 390198 (C4 (Web Text))

Max Activating Token Index: 599

Text #10

Max Range: 1.2592. Min Range: -1.2592

Max Act: 1.1542. Min Act: -0.0001

Data Index: 116850 (C4 (Web Text))

Max Activating Token Index: 551

Text #11

Max Range: 1.2592. Min Range: -1.2592

Max Act: 1.1670. Min Act: -0.0001

Data Index: 1317535 (C4 (Web Text))

Max Activating Token Index: 152

Text #12

Max Range: 1.2592. Min Range: -1.2592

Max Act: 1.1284. Min Act: -0.0001

Data Index: 566724 (C4 (Web Text))

Max Activating Token Index: 126

Text #13

Max Range: 1.2592. Min Range: -1.2592

Max Act: 1.1015. Min Act: -0.0000

Data Index: 331345 (C4 (Web Text))

Max Activating Token Index: 101

Text #14

Max Range: 1.2592. Min Range: -1.2592

Max Act: 1.1290. Min Act: -0.0001

Data Index: 948272 (C4 (Web Text))

Max Activating Token Index: 113

Text #15

Max Range: 1.2592. Min Range: -1.2592

Max Act: 1.1212. Min Act: -0.0001

Data Index: 251273 (C4 (Web Text))

Max Activating Token Index: 216

Text #16

Max Range: 1.2592. Min Range: -1.2592

Max Act: 1.1209. Min Act: -0.0001

Data Index: 268895 (C4 (Web Text))

Max Activating Token Index: 1003

Text #17

Max Range: 1.2592. Min Range: -1.2592

Max Act: 1.1103. Min Act: -0.0001

Data Index: 702145 (C4 (Web Text))

Max Activating Token Index: 565

Text #18

Max Range: 1.2592. Min Range: -1.2592

Max Act: 1.0780. Min Act: -0.0000

Data Index: 966992 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 1.2592. Min Range: -1.2592

Max Act: 1.1051. Min Act: -0.0001

Data Index: 1466523 (Python Code)

Max Activating Token Index: 1005