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

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

Neuron 2566 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: 4.8208. Min Range: -4.8208

Max Act: 4.8208. Min Act: -0.0000

Data Index: 381231 (C4 (Web Text))

Max Activating Token Index: 6

Text #1

Max Range: 4.8208. Min Range: -4.8208

Max Act: 4.4627. Min Act: -0.0000

Data Index: 158679 (C4 (Web Text))

Max Activating Token Index: 5

Text #2

Max Range: 4.8208. Min Range: -4.8208

Max Act: 3.8741. Min Act: -0.0000

Data Index: 1092002 (C4 (Web Text))

Max Activating Token Index: 8

Text #3

Max Range: 4.8208. Min Range: -4.8208

Max Act: 3.8852. Min Act: -0.0000

Data Index: 1355156 (C4 (Web Text))

Max Activating Token Index: 496

Text #4

Max Range: 4.8208. Min Range: -4.8208

Max Act: 3.5694. Min Act: -0.0000

Data Index: 647580 (C4 (Web Text))

Max Activating Token Index: 5

Text #5

Max Range: 4.8208. Min Range: -4.8208

Max Act: 3.4464. Min Act: -0.0000

Data Index: 1352703 (C4 (Web Text))

Max Activating Token Index: 1003

Text #6

Max Range: 4.8208. Min Range: -4.8208

Max Act: 3.6073. Min Act: -0.0000

Data Index: 566776 (C4 (Web Text))

Max Activating Token Index: 368

Text #7

Max Range: 4.8208. Min Range: -4.8208

Max Act: 3.3475. Min Act: -0.0000

Data Index: 1303392 (C4 (Web Text))

Max Activating Token Index: 8

Text #8

Max Range: 4.8208. Min Range: -4.8208

Max Act: 3.3305. Min Act: -0.0000

Data Index: 540771 (C4 (Web Text))

Max Activating Token Index: 8

Text #9

Max Range: 4.8208. Min Range: -4.8208

Max Act: 3.3419. Min Act: -0.0000

Data Index: 1304093 (C4 (Web Text))

Max Activating Token Index: 341

Text #10

Max Range: 4.8208. Min Range: -4.8208

Max Act: 3.3310. Min Act: -0.0000

Data Index: 183470 (C4 (Web Text))

Max Activating Token Index: 243

Text #11

Max Range: 4.8208. Min Range: -4.8208

Max Act: 3.1529. Min Act: -0.0000

Data Index: 1265207 (C4 (Web Text))

Max Activating Token Index: 11

Text #12

Max Range: 4.8208. Min Range: -4.8208

Max Act: 3.0819. Min Act: -0.0000

Data Index: 642883 (C4 (Web Text))

Max Activating Token Index: 114

Text #13

Max Range: 4.8208. Min Range: -4.8208

Max Act: 3.3683. Min Act: -0.0000

Data Index: 523588 (C4 (Web Text))

Max Activating Token Index: 724

Text #14

Max Range: 4.8208. Min Range: -4.8208

Max Act: 3.1892. Min Act: -0.0000

Data Index: 930276 (C4 (Web Text))

Max Activating Token Index: 7

Text #15

Max Range: 4.8208. Min Range: -4.8208

Max Act: 3.1986. Min Act: -0.0000

Data Index: 423750 (C4 (Web Text))

Max Activating Token Index: 442

Text #16

Max Range: 4.8208. Min Range: -4.8208

Max Act: 3.0267. Min Act: -0.0000

Data Index: 1046120 (C4 (Web Text))

Max Activating Token Index: 980

Text #17

Max Range: 4.8208. Min Range: -4.8208

Max Act: 3.0983. Min Act: -0.0000

Data Index: 771249 (C4 (Web Text))

Max Activating Token Index: 604

Text #18

Max Range: 4.8208. Min Range: -4.8208

Max Act: 3.0877. Min Act: -0.0000

Data Index: 189394 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 4.8208. Min Range: -4.8208

Max Act: 3.0395. Min Act: -0.0000

Data Index: 1321644 (C4 (Web Text))

Max Activating Token Index: 47