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

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

Neuron 4287 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5990. Min Range: -0.5990

Max Act: 0.5990. Min Act: 0.0000

Data Index: 1070510 (C4 (Web Text))

Max Activating Token Index: 554

Text #1

Max Range: 0.5990. Min Range: -0.5990

Max Act: 0.5675. Min Act: -0.0000

Data Index: 722163 (C4 (Web Text))

Max Activating Token Index: 225

Text #2

Max Range: 0.5990. Min Range: -0.5990

Max Act: 0.5626. Min Act: -0.0000

Data Index: 104123 (C4 (Web Text))

Max Activating Token Index: 576

Text #3

Max Range: 0.5990. Min Range: -0.5990

Max Act: 0.5453. Min Act: 0.0000

Data Index: 743624 (C4 (Web Text))

Max Activating Token Index: 810

Text #4

Max Range: 0.5990. Min Range: -0.5990

Max Act: 0.5182. Min Act: -0.0000

Data Index: 1310264 (C4 (Web Text))

Max Activating Token Index: 648

Text #5

Max Range: 0.5990. Min Range: -0.5990

Max Act: 0.5030. Min Act: -0.0000

Data Index: 819689 (C4 (Web Text))

Max Activating Token Index: 1001

Text #6

Max Range: 0.5990. Min Range: -0.5990

Max Act: 0.4874. Min Act: -0.0000

Data Index: 507148 (C4 (Web Text))

Max Activating Token Index: 359

Text #7

Max Range: 0.5990. Min Range: -0.5990

Max Act: 0.4316. Min Act: -0.0000

Data Index: 1257195 (C4 (Web Text))

Max Activating Token Index: 930

Text #8

Max Range: 0.5990. Min Range: -0.5990

Max Act: 0.4648. Min Act: 0.0000

Data Index: 785889 (C4 (Web Text))

Max Activating Token Index: 900

Text #9

Max Range: 0.5990. Min Range: -0.5990

Max Act: 0.4490. Min Act: -0.0000

Data Index: 399155 (C4 (Web Text))

Max Activating Token Index: 608

Text #10

Max Range: 0.5990. Min Range: -0.5990

Max Act: 0.4423. Min Act: -0.0000

Data Index: 37829 (C4 (Web Text))

Max Activating Token Index: 991

Text #11

Max Range: 0.5990. Min Range: -0.5990

Max Act: 0.4553. Min Act: -0.0000

Data Index: 1518669 (Python Code)

Max Activating Token Index: 102

Text #12

Max Range: 0.5990. Min Range: -0.5990

Max Act: 0.4323. Min Act: -0.0000

Data Index: 1493115 (Python Code)

Max Activating Token Index: 931

Text #13

Max Range: 0.5990. Min Range: -0.5990

Max Act: 0.4171. Min Act: -0.0000

Data Index: 552874 (C4 (Web Text))

Max Activating Token Index: 471

Text #14

Max Range: 0.5990. Min Range: -0.5990

Max Act: 0.4140. Min Act: 0.0000

Data Index: 264853 (C4 (Web Text))

Max Activating Token Index: 663

Text #15

Max Range: 0.5990. Min Range: -0.5990

Max Act: 0.4267. Min Act: -0.0000

Data Index: 649992 (C4 (Web Text))

Max Activating Token Index: 318

Text #16

Max Range: 0.5990. Min Range: -0.5990

Max Act: 0.4326. Min Act: -0.0000

Data Index: 614170 (C4 (Web Text))

Max Activating Token Index: 190

Text #17

Max Range: 0.5990. Min Range: -0.5990

Max Act: 0.4180. Min Act: -0.0000

Data Index: 522598 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.5990. Min Range: -0.5990

Max Act: 0.4066. Min Act: -0.0000

Data Index: 1330982 (C4 (Web Text))

Max Activating Token Index: 213

Text #19

Max Range: 0.5990. Min Range: -0.5990

Max Act: 0.4111. Min Act: -0.0000

Data Index: 245300 (C4 (Web Text))

Max Activating Token Index: 529