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

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

Neuron 5082 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: 3.8225. Min Range: -3.8225

Max Act: 3.8225. Min Act: -0.0000

Data Index: 576178 (C4 (Web Text))

Max Activating Token Index: 250

Text #1

Max Range: 3.8225. Min Range: -3.8225

Max Act: 3.7843. Min Act: -0.0000

Data Index: 1349510 (C4 (Web Text))

Max Activating Token Index: 435

Text #2

Max Range: 3.8225. Min Range: -3.8225

Max Act: 3.6425. Min Act: -0.0000

Data Index: 1004625 (C4 (Web Text))

Max Activating Token Index: 268

Text #3

Max Range: 3.8225. Min Range: -3.8225

Max Act: 3.4747. Min Act: -0.0001

Data Index: 898461 (C4 (Web Text))

Max Activating Token Index: 327

Text #4

Max Range: 3.8225. Min Range: -3.8225

Max Act: 3.4048. Min Act: -0.0001

Data Index: 996590 (C4 (Web Text))

Max Activating Token Index: 966

Text #5

Max Range: 3.8225. Min Range: -3.8225

Max Act: 3.6456. Min Act: -0.0000

Data Index: 99635 (C4 (Web Text))

Max Activating Token Index: 218

Text #6

Max Range: 3.8225. Min Range: -3.8225

Max Act: 3.5019. Min Act: -0.0000

Data Index: 147537 (C4 (Web Text))

Max Activating Token Index: 557

Text #7

Max Range: 3.8225. Min Range: -3.8225

Max Act: 3.5974. Min Act: -0.0000

Data Index: 448315 (C4 (Web Text))

Max Activating Token Index: 217

Text #8

Max Range: 3.8225. Min Range: -3.8225

Max Act: 3.2432. Min Act: -0.0000

Data Index: 1087058 (C4 (Web Text))

Max Activating Token Index: 373

Text #9

Max Range: 3.8225. Min Range: -3.8225

Max Act: 3.3654. Min Act: -0.0000

Data Index: 1001170 (C4 (Web Text))

Max Activating Token Index: 217

Text #10

Max Range: 3.8225. Min Range: -3.8225

Max Act: 3.3319. Min Act: -0.0000

Data Index: 291022 (C4 (Web Text))

Max Activating Token Index: 378

Text #11

Max Range: 3.8225. Min Range: -3.8225

Max Act: 2.9145. Min Act: -0.0000

Data Index: 219265 (C4 (Web Text))

Max Activating Token Index: 423

Text #12

Max Range: 3.8225. Min Range: -3.8225

Max Act: 3.2569. Min Act: -0.0001

Data Index: 580024 (C4 (Web Text))

Max Activating Token Index: 431

Text #13

Max Range: 3.8225. Min Range: -3.8225

Max Act: 3.3974. Min Act: -0.0000

Data Index: 494468 (C4 (Web Text))

Max Activating Token Index: 256

Text #14

Max Range: 3.8225. Min Range: -3.8225

Max Act: 3.1125. Min Act: -0.0000

Data Index: 937760 (C4 (Web Text))

Max Activating Token Index: 445

Text #15

Max Range: 3.8225. Min Range: -3.8225

Max Act: 3.2316. Min Act: -0.0000

Data Index: 589326 (C4 (Web Text))

Max Activating Token Index: 396

Text #16

Max Range: 3.8225. Min Range: -3.8225

Max Act: 3.0748. Min Act: -0.0000

Data Index: 1336117 (C4 (Web Text))

Max Activating Token Index: 854

Text #17

Max Range: 3.8225. Min Range: -3.8225

Max Act: 3.0478. Min Act: -0.0000

Data Index: 958550 (C4 (Web Text))

Max Activating Token Index: 215

Text #18

Max Range: 3.8225. Min Range: -3.8225

Max Act: 2.9255. Min Act: -0.0000

Data Index: 791332 (C4 (Web Text))

Max Activating Token Index: 226

Text #19

Max Range: 3.8225. Min Range: -3.8225

Max Act: 3.2042. Min Act: -0.0000

Data Index: 815823 (C4 (Web Text))

Max Activating Token Index: 752