Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1654 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7341. Min Range: -0.7341

Max Act: 0.7341. Min Act: -0.0000

Data Index: 651468 (C4 (Web Text))

Max Activating Token Index: 155

Text #1

Max Range: 0.7341. Min Range: -0.7341

Max Act: 0.7034. Min Act: -0.0000

Data Index: 135043 (C4 (Web Text))

Max Activating Token Index: 287

Text #2

Max Range: 0.7341. Min Range: -0.7341

Max Act: 0.6310. Min Act: -0.0001

Data Index: 691617 (C4 (Web Text))

Max Activating Token Index: 416

Text #3

Max Range: 0.7341. Min Range: -0.7341

Max Act: 0.5929. Min Act: -0.0000

Data Index: 25210 (C4 (Web Text))

Max Activating Token Index: 151

Text #4

Max Range: 0.7341. Min Range: -0.7341

Max Act: 0.6000. Min Act: -0.0001

Data Index: 1270654 (C4 (Web Text))

Max Activating Token Index: 568

Text #5

Max Range: 0.7341. Min Range: -0.7341

Max Act: 0.5321. Min Act: -0.0001

Data Index: 894725 (C4 (Web Text))

Max Activating Token Index: 99

Text #6

Max Range: 0.7341. Min Range: -0.7341

Max Act: 0.5440. Min Act: -0.0001

Data Index: 1010241 (C4 (Web Text))

Max Activating Token Index: 284

Text #7

Max Range: 0.7341. Min Range: -0.7341

Max Act: 0.5171. Min Act: -0.0001

Data Index: 1057292 (C4 (Web Text))

Max Activating Token Index: 833

Text #8

Max Range: 0.7341. Min Range: -0.7341

Max Act: 0.4856. Min Act: -0.0001

Data Index: 1114194 (C4 (Web Text))

Max Activating Token Index: 470

Text #9

Max Range: 0.7341. Min Range: -0.7341

Max Act: 0.4837. Min Act: -0.0001

Data Index: 802347 (C4 (Web Text))

Max Activating Token Index: 323

Text #10

Max Range: 0.7341. Min Range: -0.7341

Max Act: 0.4718. Min Act: -0.0001

Data Index: 420175 (C4 (Web Text))

Max Activating Token Index: 364

Text #11

Max Range: 0.7341. Min Range: -0.7341

Max Act: 0.4648. Min Act: -0.0001

Data Index: 1128434 (C4 (Web Text))

Max Activating Token Index: 513

Text #12

Max Range: 0.7341. Min Range: -0.7341

Max Act: 0.4643. Min Act: -0.0000

Data Index: 79643 (C4 (Web Text))

Max Activating Token Index: 149

Text #13

Max Range: 0.7341. Min Range: -0.7341

Max Act: 0.4739. Min Act: -0.0000

Data Index: 76895 (C4 (Web Text))

Max Activating Token Index: 106

Text #14

Max Range: 0.7341. Min Range: -0.7341

Max Act: 0.4495. Min Act: -0.0000

Data Index: 1062185 (C4 (Web Text))

Max Activating Token Index: 759

Text #15

Max Range: 0.7341. Min Range: -0.7341

Max Act: 0.4605. Min Act: -0.0001

Data Index: 145727 (C4 (Web Text))

Max Activating Token Index: 1014

Text #16

Max Range: 0.7341. Min Range: -0.7341

Max Act: 0.4593. Min Act: -0.0001

Data Index: 398878 (C4 (Web Text))

Max Activating Token Index: 585

Text #17

Max Range: 0.7341. Min Range: -0.7341

Max Act: 0.4188. Min Act: -0.0001

Data Index: 1211421 (C4 (Web Text))

Max Activating Token Index: 164

Text #18

Max Range: 0.7341. Min Range: -0.7341

Max Act: 0.4322. Min Act: -0.0001

Data Index: 1254822 (C4 (Web Text))

Max Activating Token Index: 999

Text #19

Max Range: 0.7341. Min Range: -0.7341

Max Act: 0.4304. Min Act: -0.0000

Data Index: 1169564 (C4 (Web Text))

Max Activating Token Index: 369