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

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

Neuron 4600 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7002. Min Range: -0.7002

Max Act: 0.7002. Min Act: -0.0000

Data Index: 1034469 (C4 (Web Text))

Max Activating Token Index: 146

Text #1

Max Range: 0.7002. Min Range: -0.7002

Max Act: 0.4867. Min Act: -0.0000

Data Index: 336080 (C4 (Web Text))

Max Activating Token Index: 418

Text #2

Max Range: 0.7002. Min Range: -0.7002

Max Act: 0.4485. Min Act: -0.0000

Data Index: 1464762 (Python Code)

Max Activating Token Index: 500

Text #3

Max Range: 0.7002. Min Range: -0.7002

Max Act: 0.4342. Min Act: -0.0000

Data Index: 666322 (C4 (Web Text))

Max Activating Token Index: 695

Text #4

Max Range: 0.7002. Min Range: -0.7002

Max Act: 0.4062. Min Act: -0.0000

Data Index: 152803 (C4 (Web Text))

Max Activating Token Index: 940

Text #5

Max Range: 0.7002. Min Range: -0.7002

Max Act: 0.4324. Min Act: -0.0000

Data Index: 872460 (C4 (Web Text))

Max Activating Token Index: 626

Text #6

Max Range: 0.7002. Min Range: -0.7002

Max Act: 0.4106. Min Act: -0.0000

Data Index: 1179691 (C4 (Web Text))

Max Activating Token Index: 609

Text #7

Max Range: 0.7002. Min Range: -0.7002

Max Act: 0.4216. Min Act: -0.0000

Data Index: 939866 (C4 (Web Text))

Max Activating Token Index: 940

Text #8

Max Range: 0.7002. Min Range: -0.7002

Max Act: 0.4085. Min Act: -0.0000

Data Index: 340193 (C4 (Web Text))

Max Activating Token Index: 875

Text #9

Max Range: 0.7002. Min Range: -0.7002

Max Act: 0.3956. Min Act: -0.0000

Data Index: 694890 (C4 (Web Text))

Max Activating Token Index: 360

Text #10

Max Range: 0.7002. Min Range: -0.7002

Max Act: 0.4038. Min Act: -0.0000

Data Index: 352123 (C4 (Web Text))

Max Activating Token Index: 939

Text #11

Max Range: 0.7002. Min Range: -0.7002

Max Act: 0.3973. Min Act: -0.0000

Data Index: 34117 (C4 (Web Text))

Max Activating Token Index: 474

Text #12

Max Range: 0.7002. Min Range: -0.7002

Max Act: 0.4070. Min Act: -0.0000

Data Index: 933903 (C4 (Web Text))

Max Activating Token Index: 342

Text #13

Max Range: 0.7002. Min Range: -0.7002

Max Act: 0.3888. Min Act: -0.0000

Data Index: 612760 (C4 (Web Text))

Max Activating Token Index: 227

Text #14

Max Range: 0.7002. Min Range: -0.7002

Max Act: 0.3880. Min Act: -0.0000

Data Index: 1284568 (C4 (Web Text))

Max Activating Token Index: 596

Text #15

Max Range: 0.7002. Min Range: -0.7002

Max Act: 0.3970. Min Act: -0.0000

Data Index: 1421089 (Python Code)

Max Activating Token Index: 432

Text #16

Max Range: 0.7002. Min Range: -0.7002

Max Act: 0.3831. Min Act: -0.0000

Data Index: 1047171 (C4 (Web Text))

Max Activating Token Index: 226

Text #17

Max Range: 0.7002. Min Range: -0.7002

Max Act: 0.3987. Min Act: -0.0000

Data Index: 939869 (C4 (Web Text))

Max Activating Token Index: 382

Text #18

Max Range: 0.7002. Min Range: -0.7002

Max Act: 0.3818. Min Act: -0.0000

Data Index: 234234 (C4 (Web Text))

Max Activating Token Index: 831

Text #19

Max Range: 0.7002. Min Range: -0.7002

Max Act: 0.3769. Min Act: -0.0000

Data Index: 1631298 (Python Code)

Max Activating Token Index: 460