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

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

Neuron 3194 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9555. Min Range: -1.9555

Max Act: 1.9555. Min Act: -0.0000

Data Index: 43150 (C4 (Web Text))

Max Activating Token Index: 737

Text #1

Max Range: 1.9555. Min Range: -1.9555

Max Act: 1.7420. Min Act: -0.0000

Data Index: 893882 (C4 (Web Text))

Max Activating Token Index: 365

Text #2

Max Range: 1.9555. Min Range: -1.9555

Max Act: 1.6267. Min Act: -0.0001

Data Index: 1036993 (C4 (Web Text))

Max Activating Token Index: 949

Text #3

Max Range: 1.9555. Min Range: -1.9555

Max Act: 1.6274. Min Act: -0.0000

Data Index: 100652 (C4 (Web Text))

Max Activating Token Index: 334

Text #4

Max Range: 1.9555. Min Range: -1.9555

Max Act: 1.7047. Min Act: -0.0001

Data Index: 589999 (C4 (Web Text))

Max Activating Token Index: 36

Text #5

Max Range: 1.9555. Min Range: -1.9555

Max Act: 1.8444. Min Act: -0.0000

Data Index: 947935 (C4 (Web Text))

Max Activating Token Index: 821

Text #6

Max Range: 1.9555. Min Range: -1.9555

Max Act: 1.5748. Min Act: -0.0000

Data Index: 141674 (C4 (Web Text))

Max Activating Token Index: 269

Text #7

Max Range: 1.9555. Min Range: -1.9555

Max Act: 1.4067. Min Act: -0.0001

Data Index: 1054761 (C4 (Web Text))

Max Activating Token Index: 713

Text #8

Max Range: 1.9555. Min Range: -1.9555

Max Act: 1.4989. Min Act: -0.0001

Data Index: 1059837 (C4 (Web Text))

Max Activating Token Index: 711

Text #9

Max Range: 1.9555. Min Range: -1.9555

Max Act: 1.4966. Min Act: -0.0000

Data Index: 377483 (C4 (Web Text))

Max Activating Token Index: 662

Text #10

Max Range: 1.9555. Min Range: -1.9555

Max Act: 1.4448. Min Act: -0.0001

Data Index: 1115753 (C4 (Web Text))

Max Activating Token Index: 525

Text #11

Max Range: 1.9555. Min Range: -1.9555

Max Act: 1.4122. Min Act: -0.0001

Data Index: 623251 (C4 (Web Text))

Max Activating Token Index: 159

Text #12

Max Range: 1.9555. Min Range: -1.9555

Max Act: 1.5213. Min Act: -0.0001

Data Index: 422626 (C4 (Web Text))

Max Activating Token Index: 826

Text #13

Max Range: 1.9555. Min Range: -1.9555

Max Act: 1.3786. Min Act: -0.0000

Data Index: 469493 (C4 (Web Text))

Max Activating Token Index: 703

Text #14

Max Range: 1.9555. Min Range: -1.9555

Max Act: 1.3981. Min Act: -0.0000

Data Index: 1186869 (C4 (Web Text))

Max Activating Token Index: 648

Text #15

Max Range: 1.9555. Min Range: -1.9555

Max Act: 1.2657. Min Act: -0.0000

Data Index: 419220 (C4 (Web Text))

Max Activating Token Index: 812

Text #16

Max Range: 1.9555. Min Range: -1.9555

Max Act: 1.3395. Min Act: -0.0000

Data Index: 418124 (C4 (Web Text))

Max Activating Token Index: 512

Text #17

Max Range: 1.9555. Min Range: -1.9555

Max Act: 1.4189. Min Act: -0.0000

Data Index: 372666 (C4 (Web Text))

Max Activating Token Index: 869

Text #18

Max Range: 1.9555. Min Range: -1.9555

Max Act: 1.3312. Min Act: -0.0000

Data Index: 999047 (C4 (Web Text))

Max Activating Token Index: 500

Text #19

Max Range: 1.9555. Min Range: -1.9555

Max Act: 1.3198. Min Act: -0.0001

Data Index: 222127 (C4 (Web Text))

Max Activating Token Index: 802