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

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

Neuron 686 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: 0.6409. Min Range: -0.6409

Max Act: 0.6409. Min Act: -0.0001

Data Index: 668887 (C4 (Web Text))

Max Activating Token Index: 1000

Text #1

Max Range: 0.6409. Min Range: -0.6409

Max Act: 0.5658. Min Act: -0.0001

Data Index: 154513 (C4 (Web Text))

Max Activating Token Index: 669

Text #2

Max Range: 0.6409. Min Range: -0.6409

Max Act: 0.5453. Min Act: -0.0001

Data Index: 145620 (C4 (Web Text))

Max Activating Token Index: 930

Text #3

Max Range: 0.6409. Min Range: -0.6409

Max Act: 0.5193. Min Act: -0.0000

Data Index: 196843 (C4 (Web Text))

Max Activating Token Index: 584

Text #4

Max Range: 0.6409. Min Range: -0.6409

Max Act: 0.4808. Min Act: -0.0000

Data Index: 317780 (C4 (Web Text))

Max Activating Token Index: 218

Text #5

Max Range: 0.6409. Min Range: -0.6409

Max Act: 0.4836. Min Act: -0.0000

Data Index: 745071 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 0.6409. Min Range: -0.6409

Max Act: 0.4657. Min Act: -0.0000

Data Index: 161682 (C4 (Web Text))

Max Activating Token Index: 167

Text #7

Max Range: 0.6409. Min Range: -0.6409

Max Act: 0.4437. Min Act: -0.0000

Data Index: 832407 (C4 (Web Text))

Max Activating Token Index: 206

Text #8

Max Range: 0.6409. Min Range: -0.6409

Max Act: 0.3990. Min Act: -0.0000

Data Index: 811865 (C4 (Web Text))

Max Activating Token Index: 807

Text #9

Max Range: 0.6409. Min Range: -0.6409

Max Act: 0.4402. Min Act: -0.0000

Data Index: 192178 (C4 (Web Text))

Max Activating Token Index: 365

Text #10

Max Range: 0.6409. Min Range: -0.6409

Max Act: 0.4159. Min Act: -0.0001

Data Index: 693607 (C4 (Web Text))

Max Activating Token Index: 726

Text #11

Max Range: 0.6409. Min Range: -0.6409

Max Act: 0.4256. Min Act: -0.0000

Data Index: 1021270 (C4 (Web Text))

Max Activating Token Index: 221

Text #12

Max Range: 0.6409. Min Range: -0.6409

Max Act: 0.4306. Min Act: -0.0000

Data Index: 872512 (C4 (Web Text))

Max Activating Token Index: 72

Text #13

Max Range: 0.6409. Min Range: -0.6409

Max Act: 0.3969. Min Act: -0.0000

Data Index: 25521 (C4 (Web Text))

Max Activating Token Index: 305

Text #14

Max Range: 0.6409. Min Range: -0.6409

Max Act: 0.4079. Min Act: -0.0000

Data Index: 47225 (C4 (Web Text))

Max Activating Token Index: 106

Text #15

Max Range: 0.6409. Min Range: -0.6409

Max Act: 0.4089. Min Act: -0.0001

Data Index: 487464 (C4 (Web Text))

Max Activating Token Index: 958

Text #16

Max Range: 0.6409. Min Range: -0.6409

Max Act: 0.4186. Min Act: -0.0000

Data Index: 658165 (C4 (Web Text))

Max Activating Token Index: 138

Text #17

Max Range: 0.6409. Min Range: -0.6409

Max Act: 0.4261. Min Act: -0.0001

Data Index: 397371 (C4 (Web Text))

Max Activating Token Index: 791

Text #18

Max Range: 0.6409. Min Range: -0.6409

Max Act: 0.4227. Min Act: -0.0000

Data Index: 888456 (C4 (Web Text))

Max Activating Token Index: 825

Text #19

Max Range: 0.6409. Min Range: -0.6409

Max Act: 0.4206. Min Act: -0.0001

Data Index: 1006005 (C4 (Web Text))

Max Activating Token Index: 605