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

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

Neuron 3426 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: 0.8121. Min Range: -0.8121

Max Act: 0.8121. Min Act: -0.0001

Data Index: 222322 (C4 (Web Text))

Max Activating Token Index: 650

Text #1

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.7708. Min Act: -0.0001

Data Index: 126578 (C4 (Web Text))

Max Activating Token Index: 317

Text #2

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.7788. Min Act: -0.0001

Data Index: 1032426 (C4 (Web Text))

Max Activating Token Index: 311

Text #3

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.7288. Min Act: -0.0001

Data Index: 1194368 (C4 (Web Text))

Max Activating Token Index: 802

Text #4

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.7158. Min Act: -0.0001

Data Index: 908354 (C4 (Web Text))

Max Activating Token Index: 314

Text #5

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.7275. Min Act: -0.0001

Data Index: 561240 (C4 (Web Text))

Max Activating Token Index: 1009

Text #6

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.7009. Min Act: -0.0001

Data Index: 292387 (C4 (Web Text))

Max Activating Token Index: 760

Text #7

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.6986. Min Act: -0.0001

Data Index: 461206 (C4 (Web Text))

Max Activating Token Index: 151

Text #8

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.7127. Min Act: -0.0000

Data Index: 1201735 (C4 (Web Text))

Max Activating Token Index: 276

Text #9

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.6869. Min Act: -0.0001

Data Index: 456525 (C4 (Web Text))

Max Activating Token Index: 106

Text #10

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.6836. Min Act: -0.0001

Data Index: 1270563 (C4 (Web Text))

Max Activating Token Index: 908

Text #11

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.6561. Min Act: -0.0001

Data Index: 1000217 (C4 (Web Text))

Max Activating Token Index: 391

Text #12

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.6653. Min Act: -0.0001

Data Index: 1078344 (C4 (Web Text))

Max Activating Token Index: 269

Text #13

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.6416. Min Act: -0.0001

Data Index: 584038 (C4 (Web Text))

Max Activating Token Index: 356

Text #14

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.6239. Min Act: -0.0001

Data Index: 1044456 (C4 (Web Text))

Max Activating Token Index: 127

Text #15

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.6380. Min Act: -0.0001

Data Index: 669965 (C4 (Web Text))

Max Activating Token Index: 581

Text #16

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.6388. Min Act: -0.0001

Data Index: 660363 (C4 (Web Text))

Max Activating Token Index: 41

Text #17

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.6379. Min Act: -0.0001

Data Index: 634720 (C4 (Web Text))

Max Activating Token Index: 615

Text #18

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.6048. Min Act: -0.0001

Data Index: 776906 (C4 (Web Text))

Max Activating Token Index: 184

Text #19

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.6184. Min Act: -0.0001

Data Index: 253726 (C4 (Web Text))

Max Activating Token Index: 997