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

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

Neuron 3141 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4205. Min Range: -1.4205

Max Act: 1.4205. Min Act: -0.0000

Data Index: 1144211 (C4 (Web Text))

Max Activating Token Index: 270

Text #1

Max Range: 1.4205. Min Range: -1.4205

Max Act: 1.1360. Min Act: -0.0000

Data Index: 210736 (C4 (Web Text))

Max Activating Token Index: 497

Text #2

Max Range: 1.4205. Min Range: -1.4205

Max Act: 1.0929. Min Act: -0.0000

Data Index: 638659 (C4 (Web Text))

Max Activating Token Index: 635

Text #3

Max Range: 1.4205. Min Range: -1.4205

Max Act: 0.9865. Min Act: -0.0000

Data Index: 725225 (C4 (Web Text))

Max Activating Token Index: 701

Text #4

Max Range: 1.4205. Min Range: -1.4205

Max Act: 0.9802. Min Act: -0.0000

Data Index: 990465 (C4 (Web Text))

Max Activating Token Index: 263

Text #5

Max Range: 1.4205. Min Range: -1.4205

Max Act: 0.8735. Min Act: -0.0000

Data Index: 567616 (C4 (Web Text))

Max Activating Token Index: 453

Text #6

Max Range: 1.4205. Min Range: -1.4205

Max Act: 0.8584. Min Act: -0.0000

Data Index: 1147976 (C4 (Web Text))

Max Activating Token Index: 230

Text #7

Max Range: 1.4205. Min Range: -1.4205

Max Act: 0.8612. Min Act: -0.0000

Data Index: 858564 (C4 (Web Text))

Max Activating Token Index: 492

Text #8

Max Range: 1.4205. Min Range: -1.4205

Max Act: 0.8630. Min Act: -0.0000

Data Index: 1346012 (C4 (Web Text))

Max Activating Token Index: 560

Text #9

Max Range: 1.4205. Min Range: -1.4205

Max Act: 0.8901. Min Act: -0.0000

Data Index: 929148 (C4 (Web Text))

Max Activating Token Index: 926

Text #10

Max Range: 1.4205. Min Range: -1.4205

Max Act: 0.8736. Min Act: -0.0000

Data Index: 339806 (C4 (Web Text))

Max Activating Token Index: 96

Text #11

Max Range: 1.4205. Min Range: -1.4205

Max Act: 0.7779. Min Act: -0.0000

Data Index: 434580 (C4 (Web Text))

Max Activating Token Index: 275

Text #12

Max Range: 1.4205. Min Range: -1.4205

Max Act: 0.7802. Min Act: -0.0000

Data Index: 350651 (C4 (Web Text))

Max Activating Token Index: 78

Text #13

Max Range: 1.4205. Min Range: -1.4205

Max Act: 0.7838. Min Act: -0.0000

Data Index: 794505 (C4 (Web Text))

Max Activating Token Index: 332

Text #14

Max Range: 1.4205. Min Range: -1.4205

Max Act: 0.7673. Min Act: -0.0000

Data Index: 338535 (C4 (Web Text))

Max Activating Token Index: 78

Text #15

Max Range: 1.4205. Min Range: -1.4205

Max Act: 0.7528. Min Act: -0.0000

Data Index: 731140 (C4 (Web Text))

Max Activating Token Index: 524

Text #16

Max Range: 1.4205. Min Range: -1.4205

Max Act: 0.6706. Min Act: -0.0000

Data Index: 508824 (C4 (Web Text))

Max Activating Token Index: 816

Text #17

Max Range: 1.4205. Min Range: -1.4205

Max Act: 0.6952. Min Act: -0.0000

Data Index: 586250 (C4 (Web Text))

Max Activating Token Index: 792

Text #18

Max Range: 1.4205. Min Range: -1.4205

Max Act: 0.6972. Min Act: -0.0000

Data Index: 447500 (C4 (Web Text))

Max Activating Token Index: 918

Text #19

Max Range: 1.4205. Min Range: -1.4205

Max Act: 0.6775. Min Act: -0.0000

Data Index: 1095015 (C4 (Web Text))

Max Activating Token Index: 914