Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4202 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.9221. Min Range: -2.9221

Max Act: 2.9205. Min Act: -0.0000

Data Index: 955881 (C4 (Web Text))

Max Activating Token Index: 481

Text #1

Max Range: 2.9221. Min Range: -2.9221

Max Act: 2.9221. Min Act: -0.0000

Data Index: 1100307 (C4 (Web Text))

Max Activating Token Index: 652

Text #2

Max Range: 2.9221. Min Range: -2.9221

Max Act: 2.5945. Min Act: -0.0000

Data Index: 1332227 (C4 (Web Text))

Max Activating Token Index: 842

Text #3

Max Range: 2.9221. Min Range: -2.9221

Max Act: 2.1293. Min Act: -0.0000

Data Index: 110339 (C4 (Web Text))

Max Activating Token Index: 253

Text #4

Max Range: 2.9221. Min Range: -2.9221

Max Act: 2.0926. Min Act: -0.0000

Data Index: 269726 (C4 (Web Text))

Max Activating Token Index: 76

Text #5

Max Range: 2.9221. Min Range: -2.9221

Max Act: 2.0065. Min Act: -0.0000

Data Index: 392844 (C4 (Web Text))

Max Activating Token Index: 166

Text #6

Max Range: 2.9221. Min Range: -2.9221

Max Act: 1.9994. Min Act: -0.0000

Data Index: 498160 (C4 (Web Text))

Max Activating Token Index: 999

Text #7

Max Range: 2.9221. Min Range: -2.9221

Max Act: 2.1175. Min Act: -0.0000

Data Index: 638365 (C4 (Web Text))

Max Activating Token Index: 906

Text #8

Max Range: 2.9221. Min Range: -2.9221

Max Act: 1.9981. Min Act: -0.0000

Data Index: 193448 (C4 (Web Text))

Max Activating Token Index: 301

Text #9

Max Range: 2.9221. Min Range: -2.9221

Max Act: 1.8958. Min Act: -0.0000

Data Index: 1026617 (C4 (Web Text))

Max Activating Token Index: 988

Text #10

Max Range: 2.9221. Min Range: -2.9221

Max Act: 1.9859. Min Act: -0.0000

Data Index: 1337484 (C4 (Web Text))

Max Activating Token Index: 263

Text #11

Max Range: 2.9221. Min Range: -2.9221

Max Act: 2.0699. Min Act: -0.0000

Data Index: 869455 (C4 (Web Text))

Max Activating Token Index: 915

Text #12

Max Range: 2.9221. Min Range: -2.9221

Max Act: 1.9173. Min Act: -0.0000

Data Index: 1152795 (C4 (Web Text))

Max Activating Token Index: 518

Text #13

Max Range: 2.9221. Min Range: -2.9221

Max Act: 1.8975. Min Act: -0.0000

Data Index: 272690 (C4 (Web Text))

Max Activating Token Index: 25

Text #14

Max Range: 2.9221. Min Range: -2.9221

Max Act: 1.8714. Min Act: -0.0000

Data Index: 867518 (C4 (Web Text))

Max Activating Token Index: 414

Text #15

Max Range: 2.9221. Min Range: -2.9221

Max Act: 1.8595. Min Act: -0.0000

Data Index: 876683 (C4 (Web Text))

Max Activating Token Index: 134

Text #16

Max Range: 2.9221. Min Range: -2.9221

Max Act: 1.8135. Min Act: -0.0000

Data Index: 192086 (C4 (Web Text))

Max Activating Token Index: 311

Text #17

Max Range: 2.9221. Min Range: -2.9221

Max Act: 1.7937. Min Act: -0.0000

Data Index: 598132 (C4 (Web Text))

Max Activating Token Index: 1006

Text #18

Max Range: 2.9221. Min Range: -2.9221

Max Act: 1.7359. Min Act: -0.0000

Data Index: 655411 (C4 (Web Text))

Max Activating Token Index: 358

Text #19

Max Range: 2.9221. Min Range: -2.9221

Max Act: 1.7653. Min Act: -0.0000

Data Index: 645037 (C4 (Web Text))

Max Activating Token Index: 400