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

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

Neuron 4956 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6876. Min Range: -3.6876

Max Act: 3.6876. Min Act: -0.0000

Data Index: 117270 (C4 (Web Text))

Max Activating Token Index: 252

Text #1

Max Range: 3.6876. Min Range: -3.6876

Max Act: 2.9857. Min Act: -0.0000

Data Index: 932027 (C4 (Web Text))

Max Activating Token Index: 908

Text #2

Max Range: 3.6876. Min Range: -3.6876

Max Act: 2.9979. Min Act: -0.0000

Data Index: 981699 (C4 (Web Text))

Max Activating Token Index: 281

Text #3

Max Range: 3.6876. Min Range: -3.6876

Max Act: 2.9028. Min Act: -0.0000

Data Index: 1109620 (C4 (Web Text))

Max Activating Token Index: 846

Text #4

Max Range: 3.6876. Min Range: -3.6876

Max Act: 2.8768. Min Act: -0.0000

Data Index: 1260347 (C4 (Web Text))

Max Activating Token Index: 551

Text #5

Max Range: 3.6876. Min Range: -3.6876

Max Act: 2.7161. Min Act: -0.0000

Data Index: 1092865 (C4 (Web Text))

Max Activating Token Index: 605

Text #6

Max Range: 3.6876. Min Range: -3.6876

Max Act: 2.6942. Min Act: -0.0000

Data Index: 932225 (C4 (Web Text))

Max Activating Token Index: 667

Text #7

Max Range: 3.6876. Min Range: -3.6876

Max Act: 2.7055. Min Act: -0.0000

Data Index: 1278695 (C4 (Web Text))

Max Activating Token Index: 747

Text #8

Max Range: 3.6876. Min Range: -3.6876

Max Act: 2.4280. Min Act: -0.0000

Data Index: 323090 (C4 (Web Text))

Max Activating Token Index: 447

Text #9

Max Range: 3.6876. Min Range: -3.6876

Max Act: 2.6967. Min Act: -0.0000

Data Index: 1091011 (C4 (Web Text))

Max Activating Token Index: 929

Text #10

Max Range: 3.6876. Min Range: -3.6876

Max Act: 2.6614. Min Act: -0.0000

Data Index: 1241079 (C4 (Web Text))

Max Activating Token Index: 188

Text #11

Max Range: 3.6876. Min Range: -3.6876

Max Act: 2.5105. Min Act: -0.0000

Data Index: 336278 (C4 (Web Text))

Max Activating Token Index: 1006

Text #12

Max Range: 3.6876. Min Range: -3.6876

Max Act: 2.4863. Min Act: -0.0000

Data Index: 886282 (C4 (Web Text))

Max Activating Token Index: 190

Text #13

Max Range: 3.6876. Min Range: -3.6876

Max Act: 2.4741. Min Act: -0.0000

Data Index: 822918 (C4 (Web Text))

Max Activating Token Index: 477

Text #14

Max Range: 3.6876. Min Range: -3.6876

Max Act: 2.3647. Min Act: -0.0000

Data Index: 134654 (C4 (Web Text))

Max Activating Token Index: 35

Text #15

Max Range: 3.6876. Min Range: -3.6876

Max Act: 2.4590. Min Act: -0.0000

Data Index: 183304 (C4 (Web Text))

Max Activating Token Index: 537

Text #16

Max Range: 3.6876. Min Range: -3.6876

Max Act: 2.4305. Min Act: -0.0000

Data Index: 30156 (C4 (Web Text))

Max Activating Token Index: 700

Text #17

Max Range: 3.6876. Min Range: -3.6876

Max Act: 2.4412. Min Act: -0.0000

Data Index: 177849 (C4 (Web Text))

Max Activating Token Index: 598

Text #18

Max Range: 3.6876. Min Range: -3.6876

Max Act: 2.2829. Min Act: -0.0000

Data Index: 1000538 (C4 (Web Text))

Max Activating Token Index: 989

Text #19

Max Range: 3.6876. Min Range: -3.6876

Max Act: 2.3958. Min Act: -0.0000

Data Index: 788468 (C4 (Web Text))

Max Activating Token Index: 544