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

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

Neuron 560 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2031. Min Range: -2.2031

Max Act: 2.2031. Min Act: -0.0000

Data Index: 1342051 (C4 (Web Text))

Max Activating Token Index: 457

Text #1

Max Range: 2.2031. Min Range: -2.2031

Max Act: 2.0107. Min Act: -0.0000

Data Index: 989217 (C4 (Web Text))

Max Activating Token Index: 462

Text #2

Max Range: 2.2031. Min Range: -2.2031

Max Act: 2.1185. Min Act: -0.0000

Data Index: 550905 (C4 (Web Text))

Max Activating Token Index: 295

Text #3

Max Range: 2.2031. Min Range: -2.2031

Max Act: 1.8748. Min Act: -0.0000

Data Index: 636877 (C4 (Web Text))

Max Activating Token Index: 978

Text #4

Max Range: 2.2031. Min Range: -2.2031

Max Act: 1.7480. Min Act: -0.0000

Data Index: 268512 (C4 (Web Text))

Max Activating Token Index: 774

Text #5

Max Range: 2.2031. Min Range: -2.2031

Max Act: 1.6533. Min Act: -0.0000

Data Index: 501178 (C4 (Web Text))

Max Activating Token Index: 942

Text #6

Max Range: 2.2031. Min Range: -2.2031

Max Act: 1.7032. Min Act: -0.0000

Data Index: 1008028 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 2.2031. Min Range: -2.2031

Max Act: 1.6208. Min Act: -0.0000

Data Index: 1091636 (C4 (Web Text))

Max Activating Token Index: 48

Text #8

Max Range: 2.2031. Min Range: -2.2031

Max Act: 1.4822. Min Act: -0.0000

Data Index: 490216 (C4 (Web Text))

Max Activating Token Index: 983

Text #9

Max Range: 2.2031. Min Range: -2.2031

Max Act: 1.5607. Min Act: -0.0000

Data Index: 837036 (C4 (Web Text))

Max Activating Token Index: 518

Text #10

Max Range: 2.2031. Min Range: -2.2031

Max Act: 1.5276. Min Act: -0.0000

Data Index: 612893 (C4 (Web Text))

Max Activating Token Index: 834

Text #11

Max Range: 2.2031. Min Range: -2.2031

Max Act: 1.5277. Min Act: -0.0000

Data Index: 139744 (C4 (Web Text))

Max Activating Token Index: 1011

Text #12

Max Range: 2.2031. Min Range: -2.2031

Max Act: 1.5117. Min Act: -0.0000

Data Index: 102423 (C4 (Web Text))

Max Activating Token Index: 36

Text #13

Max Range: 2.2031. Min Range: -2.2031

Max Act: 1.4062. Min Act: -0.0000

Data Index: 189741 (C4 (Web Text))

Max Activating Token Index: 7

Text #14

Max Range: 2.2031. Min Range: -2.2031

Max Act: 1.3991. Min Act: -0.0000

Data Index: 591068 (C4 (Web Text))

Max Activating Token Index: 838

Text #15

Max Range: 2.2031. Min Range: -2.2031

Max Act: 1.4775. Min Act: -0.0000

Data Index: 152286 (C4 (Web Text))

Max Activating Token Index: 347

Text #16

Max Range: 2.2031. Min Range: -2.2031

Max Act: 1.4609. Min Act: -0.0000

Data Index: 463407 (C4 (Web Text))

Max Activating Token Index: 1007

Text #17

Max Range: 2.2031. Min Range: -2.2031

Max Act: 1.4586. Min Act: -0.0000

Data Index: 1161721 (C4 (Web Text))

Max Activating Token Index: 50

Text #18

Max Range: 2.2031. Min Range: -2.2031

Max Act: 1.4445. Min Act: -0.0000

Data Index: 1240033 (C4 (Web Text))

Max Activating Token Index: 988

Text #19

Max Range: 2.2031. Min Range: -2.2031

Max Act: 1.3403. Min Act: -0.0000

Data Index: 467970 (C4 (Web Text))

Max Activating Token Index: 879