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

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

Neuron 4798 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.6986. Min Act: -0.0000

Data Index: 450456 (C4 (Web Text))

Max Activating Token Index: 309

Text #1

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.6144. Min Act: -0.0000

Data Index: 346619 (C4 (Web Text))

Max Activating Token Index: 270

Text #2

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.5494. Min Act: -0.0000

Data Index: 596825 (C4 (Web Text))

Max Activating Token Index: 731

Text #3

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.5358. Min Act: -0.0000

Data Index: 973482 (C4 (Web Text))

Max Activating Token Index: 586

Text #4

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.5536. Min Act: -0.0000

Data Index: 744604 (C4 (Web Text))

Max Activating Token Index: 218

Text #5

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.4978. Min Act: -0.0000

Data Index: 306801 (C4 (Web Text))

Max Activating Token Index: 288

Text #6

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.4881. Min Act: -0.0000

Data Index: 334166 (C4 (Web Text))

Max Activating Token Index: 577

Text #7

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.5054. Min Act: -0.0000

Data Index: 610680 (C4 (Web Text))

Max Activating Token Index: 112

Text #8

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.4940. Min Act: -0.0000

Data Index: 287493 (C4 (Web Text))

Max Activating Token Index: 707

Text #9

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.4700. Min Act: -0.0000

Data Index: 741740 (C4 (Web Text))

Max Activating Token Index: 342

Text #10

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.4512. Min Act: -0.0000

Data Index: 105252 (C4 (Web Text))

Max Activating Token Index: 630

Text #11

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.4795. Min Act: -0.0000

Data Index: 617908 (C4 (Web Text))

Max Activating Token Index: 301

Text #12

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.4630. Min Act: -0.0000

Data Index: 335677 (C4 (Web Text))

Max Activating Token Index: 874

Text #13

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.4474. Min Act: -0.0000

Data Index: 688719 (C4 (Web Text))

Max Activating Token Index: 277

Text #14

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.4293. Min Act: -0.0000

Data Index: 1045206 (C4 (Web Text))

Max Activating Token Index: 416

Text #15

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.4422. Min Act: -0.0000

Data Index: 297931 (C4 (Web Text))

Max Activating Token Index: 73

Text #16

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.4553. Min Act: -0.0000

Data Index: 379668 (C4 (Web Text))

Max Activating Token Index: 463

Text #17

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.4530. Min Act: -0.0000

Data Index: 723868 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.4366. Min Act: -0.0000

Data Index: 807515 (C4 (Web Text))

Max Activating Token Index: 136

Text #19

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.4282. Min Act: -0.0000

Data Index: 1007365 (C4 (Web Text))

Max Activating Token Index: 754