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

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

Neuron 4604 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5077. Min Range: -0.5077

Max Act: 0.5077. Min Act: -0.0000

Data Index: 1222712 (C4 (Web Text))

Max Activating Token Index: 63

Text #1

Max Range: 0.5077. Min Range: -0.5077

Max Act: 0.4476. Min Act: -0.0000

Data Index: 1286962 (C4 (Web Text))

Max Activating Token Index: 867

Text #2

Max Range: 0.5077. Min Range: -0.5077

Max Act: 0.4285. Min Act: -0.0000

Data Index: 1299647 (C4 (Web Text))

Max Activating Token Index: 284

Text #3

Max Range: 0.5077. Min Range: -0.5077

Max Act: 0.4335. Min Act: -0.0000

Data Index: 316081 (C4 (Web Text))

Max Activating Token Index: 740

Text #4

Max Range: 0.5077. Min Range: -0.5077

Max Act: 0.4480. Min Act: -0.0000

Data Index: 151678 (C4 (Web Text))

Max Activating Token Index: 929

Text #5

Max Range: 0.5077. Min Range: -0.5077

Max Act: 0.4257. Min Act: -0.0000

Data Index: 309547 (C4 (Web Text))

Max Activating Token Index: 630

Text #6

Max Range: 0.5077. Min Range: -0.5077

Max Act: 0.4085. Min Act: -0.0000

Data Index: 661329 (C4 (Web Text))

Max Activating Token Index: 713

Text #7

Max Range: 0.5077. Min Range: -0.5077

Max Act: 0.4199. Min Act: -0.0000

Data Index: 38125 (C4 (Web Text))

Max Activating Token Index: 830

Text #8

Max Range: 0.5077. Min Range: -0.5077

Max Act: 0.4047. Min Act: -0.0000

Data Index: 138383 (C4 (Web Text))

Max Activating Token Index: 322

Text #9

Max Range: 0.5077. Min Range: -0.5077

Max Act: 0.4181. Min Act: -0.0000

Data Index: 310431 (C4 (Web Text))

Max Activating Token Index: 602

Text #10

Max Range: 0.5077. Min Range: -0.5077

Max Act: 0.4153. Min Act: -0.0000

Data Index: 982291 (C4 (Web Text))

Max Activating Token Index: 846

Text #11

Max Range: 0.5077. Min Range: -0.5077

Max Act: 0.3980. Min Act: -0.0000

Data Index: 1074000 (C4 (Web Text))

Max Activating Token Index: 392

Text #12

Max Range: 0.5077. Min Range: -0.5077

Max Act: 0.4326. Min Act: -0.0000

Data Index: 1231049 (C4 (Web Text))

Max Activating Token Index: 837

Text #13

Max Range: 0.5077. Min Range: -0.5077

Max Act: 0.4152. Min Act: -0.0000

Data Index: 215133 (C4 (Web Text))

Max Activating Token Index: 846

Text #14

Max Range: 0.5077. Min Range: -0.5077

Max Act: 0.4138. Min Act: -0.0000

Data Index: 1043708 (C4 (Web Text))

Max Activating Token Index: 323

Text #15

Max Range: 0.5077. Min Range: -0.5077

Max Act: 0.4121. Min Act: -0.0000

Data Index: 960724 (C4 (Web Text))

Max Activating Token Index: 882

Text #16

Max Range: 0.5077. Min Range: -0.5077

Max Act: 0.4208. Min Act: -0.0000

Data Index: 500435 (C4 (Web Text))

Max Activating Token Index: 828

Text #17

Max Range: 0.5077. Min Range: -0.5077

Max Act: 0.4158. Min Act: -0.0000

Data Index: 950053 (C4 (Web Text))

Max Activating Token Index: 926

Text #18

Max Range: 0.5077. Min Range: -0.5077

Max Act: 0.4021. Min Act: -0.0000

Data Index: 25935 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 0.5077. Min Range: -0.5077

Max Act: 0.4124. Min Act: -0.0000

Data Index: 1169940 (C4 (Web Text))

Max Activating Token Index: 951