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

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

Neuron 4624 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: 0.4965. Min Range: -0.4965

Max Act: 0.4965. Min Act: -0.0000

Data Index: 1095985 (C4 (Web Text))

Max Activating Token Index: 370

Text #1

Max Range: 0.4965. Min Range: -0.4965

Max Act: 0.4552. Min Act: -0.0000

Data Index: 760755 (C4 (Web Text))

Max Activating Token Index: 1013

Text #2

Max Range: 0.4965. Min Range: -0.4965

Max Act: 0.4796. Min Act: -0.0000

Data Index: 511573 (C4 (Web Text))

Max Activating Token Index: 691

Text #3

Max Range: 0.4965. Min Range: -0.4965

Max Act: 0.4805. Min Act: -0.0000

Data Index: 1351740 (C4 (Web Text))

Max Activating Token Index: 659

Text #4

Max Range: 0.4965. Min Range: -0.4965

Max Act: 0.4223. Min Act: -0.0000

Data Index: 564889 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 0.4965. Min Range: -0.4965

Max Act: 0.4346. Min Act: -0.0000

Data Index: 626127 (C4 (Web Text))

Max Activating Token Index: 908

Text #6

Max Range: 0.4965. Min Range: -0.4965

Max Act: 0.4197. Min Act: -0.0000

Data Index: 97451 (C4 (Web Text))

Max Activating Token Index: 617

Text #7

Max Range: 0.4965. Min Range: -0.4965

Max Act: 0.4176. Min Act: -0.0000

Data Index: 238518 (C4 (Web Text))

Max Activating Token Index: 388

Text #8

Max Range: 0.4965. Min Range: -0.4965

Max Act: 0.4291. Min Act: -0.0000

Data Index: 1285108 (C4 (Web Text))

Max Activating Token Index: 864

Text #9

Max Range: 0.4965. Min Range: -0.4965

Max Act: 0.4302. Min Act: -0.0000

Data Index: 444163 (C4 (Web Text))

Max Activating Token Index: 489

Text #10

Max Range: 0.4965. Min Range: -0.4965

Max Act: 0.4211. Min Act: -0.0000

Data Index: 114568 (C4 (Web Text))

Max Activating Token Index: 977

Text #11

Max Range: 0.4965. Min Range: -0.4965

Max Act: 0.4275. Min Act: -0.0000

Data Index: 254674 (C4 (Web Text))

Max Activating Token Index: 146

Text #12

Max Range: 0.4965. Min Range: -0.4965

Max Act: 0.4126. Min Act: -0.0000

Data Index: 921848 (C4 (Web Text))

Max Activating Token Index: 451

Text #13

Max Range: 0.4965. Min Range: -0.4965

Max Act: 0.3930. Min Act: -0.0000

Data Index: 1110790 (C4 (Web Text))

Max Activating Token Index: 792

Text #14

Max Range: 0.4965. Min Range: -0.4965

Max Act: 0.3930. Min Act: -0.0000

Data Index: 766425 (C4 (Web Text))

Max Activating Token Index: 1010

Text #15

Max Range: 0.4965. Min Range: -0.4965

Max Act: 0.4000. Min Act: -0.0000

Data Index: 742883 (C4 (Web Text))

Max Activating Token Index: 955

Text #16

Max Range: 0.4965. Min Range: -0.4965

Max Act: 0.3964. Min Act: -0.0000

Data Index: 1352210 (C4 (Web Text))

Max Activating Token Index: 780

Text #17

Max Range: 0.4965. Min Range: -0.4965

Max Act: 0.4090. Min Act: -0.0000

Data Index: 428446 (C4 (Web Text))

Max Activating Token Index: 205

Text #18

Max Range: 0.4965. Min Range: -0.4965

Max Act: 0.3732. Min Act: -0.0000

Data Index: 530938 (C4 (Web Text))

Max Activating Token Index: 427

Text #19

Max Range: 0.4965. Min Range: -0.4965

Max Act: 0.3851. Min Act: -0.0000

Data Index: 1035819 (C4 (Web Text))

Max Activating Token Index: 517