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

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

Neuron 1386 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1475. Min Act: -0.0003

Data Index: 961225 (C4 (Web Text))

Max Activating Token Index: 681

Text #1

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1357. Min Act: -0.0003

Data Index: 705146 (C4 (Web Text))

Max Activating Token Index: 452

Text #2

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1253. Min Act: -0.0003

Data Index: 338809 (C4 (Web Text))

Max Activating Token Index: 189

Text #3

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1290. Min Act: -0.0003

Data Index: 207814 (C4 (Web Text))

Max Activating Token Index: 161

Text #4

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1290. Min Act: -0.0002

Data Index: 432465 (C4 (Web Text))

Max Activating Token Index: 505

Text #5

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1247. Min Act: -0.0003

Data Index: 878630 (C4 (Web Text))

Max Activating Token Index: 347

Text #6

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1231. Min Act: -0.0003

Data Index: 636181 (C4 (Web Text))

Max Activating Token Index: 487

Text #7

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1132. Min Act: -0.0003

Data Index: 1051761 (C4 (Web Text))

Max Activating Token Index: 190

Text #8

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1110. Min Act: -0.0003

Data Index: 82773 (C4 (Web Text))

Max Activating Token Index: 128

Text #9

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1077. Min Act: -0.0003

Data Index: 602171 (C4 (Web Text))

Max Activating Token Index: 619

Text #10

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1032. Min Act: -0.0003

Data Index: 162026 (C4 (Web Text))

Max Activating Token Index: 34

Text #11

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1062. Min Act: -0.0003

Data Index: 21281 (C4 (Web Text))

Max Activating Token Index: 40

Text #12

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1101. Min Act: -0.0003

Data Index: 859472 (C4 (Web Text))

Max Activating Token Index: 951

Text #13

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1051. Min Act: -0.0003

Data Index: 583187 (C4 (Web Text))

Max Activating Token Index: 644

Text #14

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1041. Min Act: -0.0003

Data Index: 854821 (C4 (Web Text))

Max Activating Token Index: 113

Text #15

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1026. Min Act: -0.0003

Data Index: 262464 (C4 (Web Text))

Max Activating Token Index: 717

Text #16

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1060. Min Act: -0.0003

Data Index: 718588 (C4 (Web Text))

Max Activating Token Index: 155

Text #17

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1011. Min Act: -0.0003

Data Index: 628740 (C4 (Web Text))

Max Activating Token Index: 615

Text #18

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1015. Min Act: -0.0003

Data Index: 709152 (C4 (Web Text))

Max Activating Token Index: 503

Text #19

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1008. Min Act: -0.0003

Data Index: 67675 (C4 (Web Text))

Max Activating Token Index: 320