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

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

Neuron 4033 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2776. Min Act: -0.0001

Data Index: 700402 (C4 (Web Text))

Max Activating Token Index: 999

Text #1

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2966. Min Act: -0.0001

Data Index: 183788 (C4 (Web Text))

Max Activating Token Index: 985

Text #2

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2711. Min Act: -0.0002

Data Index: 624715 (C4 (Web Text))

Max Activating Token Index: 948

Text #3

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2556. Min Act: -0.0002

Data Index: 845708 (C4 (Web Text))

Max Activating Token Index: 944

Text #4

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2501. Min Act: -0.0002

Data Index: 202834 (C4 (Web Text))

Max Activating Token Index: 956

Text #5

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2613. Min Act: -0.0001

Data Index: 157517 (C4 (Web Text))

Max Activating Token Index: 750

Text #6

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2622. Min Act: -0.0002

Data Index: 126746 (C4 (Web Text))

Max Activating Token Index: 690

Text #7

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2479. Min Act: -0.0001

Data Index: 675547 (C4 (Web Text))

Max Activating Token Index: 529

Text #8

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2304. Min Act: -0.0002

Data Index: 437877 (C4 (Web Text))

Max Activating Token Index: 394

Text #9

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2253. Min Act: -0.0002

Data Index: 1163505 (C4 (Web Text))

Max Activating Token Index: 501

Text #10

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2243. Min Act: -0.0002

Data Index: 333601 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2121. Min Act: -0.0002

Data Index: 167987 (C4 (Web Text))

Max Activating Token Index: 365

Text #12

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2137. Min Act: -0.0002

Data Index: 874350 (C4 (Web Text))

Max Activating Token Index: 284

Text #13

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2205. Min Act: -0.0001

Data Index: 664992 (C4 (Web Text))

Max Activating Token Index: 382

Text #14

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2045. Min Act: -0.0002

Data Index: 643509 (C4 (Web Text))

Max Activating Token Index: 418

Text #15

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2145. Min Act: -0.0002

Data Index: 784115 (C4 (Web Text))

Max Activating Token Index: 527

Text #16

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.1996. Min Act: -0.0002

Data Index: 1227195 (C4 (Web Text))

Max Activating Token Index: 162

Text #17

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.1946. Min Act: -0.0002

Data Index: 518869 (C4 (Web Text))

Max Activating Token Index: 129

Text #18

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2018. Min Act: -0.0002

Data Index: 328005 (C4 (Web Text))

Max Activating Token Index: 152

Text #19

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.1742. Min Act: -0.0002

Data Index: 1073316 (C4 (Web Text))

Max Activating Token Index: 602