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

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

Neuron 3800 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0009. Min Range: -4.0009

Max Act: 4.0009. Min Act: -0.0000

Data Index: 1089056 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 4.0009. Min Range: -4.0009

Max Act: 3.4927. Min Act: -0.0000

Data Index: 557056 (C4 (Web Text))

Max Activating Token Index: 677

Text #2

Max Range: 4.0009. Min Range: -4.0009

Max Act: 3.1029. Min Act: -0.0000

Data Index: 29206 (C4 (Web Text))

Max Activating Token Index: 330

Text #3

Max Range: 4.0009. Min Range: -4.0009

Max Act: 2.9514. Min Act: -0.0000

Data Index: 798151 (C4 (Web Text))

Max Activating Token Index: 188

Text #4

Max Range: 4.0009. Min Range: -4.0009

Max Act: 2.9456. Min Act: -0.0000

Data Index: 1291233 (C4 (Web Text))

Max Activating Token Index: 292

Text #5

Max Range: 4.0009. Min Range: -4.0009

Max Act: 2.7274. Min Act: -0.0000

Data Index: 1242885 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 4.0009. Min Range: -4.0009

Max Act: 2.5732. Min Act: -0.0000

Data Index: 42891 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 4.0009. Min Range: -4.0009

Max Act: 2.8339. Min Act: -0.0000

Data Index: 1163499 (C4 (Web Text))

Max Activating Token Index: 606

Text #8

Max Range: 4.0009. Min Range: -4.0009

Max Act: 2.6900. Min Act: 0.0000

Data Index: 616618 (C4 (Web Text))

Max Activating Token Index: 192

Text #9

Max Range: 4.0009. Min Range: -4.0009

Max Act: 2.6854. Min Act: -0.0000

Data Index: 565678 (C4 (Web Text))

Max Activating Token Index: 576

Text #10

Max Range: 4.0009. Min Range: -4.0009

Max Act: 2.8611. Min Act: 0.0000

Data Index: 1008526 (C4 (Web Text))

Max Activating Token Index: 362

Text #11

Max Range: 4.0009. Min Range: -4.0009

Max Act: 2.7313. Min Act: -0.0000

Data Index: 309849 (C4 (Web Text))

Max Activating Token Index: 964

Text #12

Max Range: 4.0009. Min Range: -4.0009

Max Act: 2.8525. Min Act: -0.0000

Data Index: 126642 (C4 (Web Text))

Max Activating Token Index: 90

Text #13

Max Range: 4.0009. Min Range: -4.0009

Max Act: 2.6850. Min Act: -0.0000

Data Index: 1244080 (C4 (Web Text))

Max Activating Token Index: 242

Text #14

Max Range: 4.0009. Min Range: -4.0009

Max Act: 2.6664. Min Act: -0.0000

Data Index: 563568 (C4 (Web Text))

Max Activating Token Index: 83

Text #15

Max Range: 4.0009. Min Range: -4.0009

Max Act: 2.6484. Min Act: -0.0000

Data Index: 114394 (C4 (Web Text))

Max Activating Token Index: 1018

Text #16

Max Range: 4.0009. Min Range: -4.0009

Max Act: 2.7749. Min Act: -0.0000

Data Index: 1009643 (C4 (Web Text))

Max Activating Token Index: 343

Text #17

Max Range: 4.0009. Min Range: -4.0009

Max Act: 2.6267. Min Act: -0.0000

Data Index: 638774 (C4 (Web Text))

Max Activating Token Index: 1013

Text #18

Max Range: 4.0009. Min Range: -4.0009

Max Act: 2.4193. Min Act: -0.0000

Data Index: 31528 (C4 (Web Text))

Max Activating Token Index: 156

Text #19

Max Range: 4.0009. Min Range: -4.0009

Max Act: 2.5461. Min Act: -0.0000

Data Index: 136378 (C4 (Web Text))

Max Activating Token Index: 1020