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

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

Neuron 1231 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7716. Min Range: -2.7716

Max Act: 2.6273. Min Act: -0.0000

Data Index: 153409 (C4 (Web Text))

Max Activating Token Index: 758

Text #1

Max Range: 2.7716. Min Range: -2.7716

Max Act: 2.7716. Min Act: -0.0000

Data Index: 41148 (C4 (Web Text))

Max Activating Token Index: 55

Text #2

Max Range: 2.7716. Min Range: -2.7716

Max Act: 2.5473. Min Act: -0.0000

Data Index: 1233457 (C4 (Web Text))

Max Activating Token Index: 183

Text #3

Max Range: 2.7716. Min Range: -2.7716

Max Act: 2.5630. Min Act: -0.0000

Data Index: 322005 (C4 (Web Text))

Max Activating Token Index: 947

Text #4

Max Range: 2.7716. Min Range: -2.7716

Max Act: 2.4399. Min Act: -0.0000

Data Index: 175536 (C4 (Web Text))

Max Activating Token Index: 699

Text #5

Max Range: 2.7716. Min Range: -2.7716

Max Act: 2.4082. Min Act: -0.0000

Data Index: 360048 (C4 (Web Text))

Max Activating Token Index: 487

Text #6

Max Range: 2.7716. Min Range: -2.7716

Max Act: 2.3417. Min Act: -0.0000

Data Index: 411566 (C4 (Web Text))

Max Activating Token Index: 733

Text #7

Max Range: 2.7716. Min Range: -2.7716

Max Act: 2.3232. Min Act: -0.0000

Data Index: 958413 (C4 (Web Text))

Max Activating Token Index: 22

Text #8

Max Range: 2.7716. Min Range: -2.7716

Max Act: 2.1965. Min Act: -0.0000

Data Index: 25367 (C4 (Web Text))

Max Activating Token Index: 786

Text #9

Max Range: 2.7716. Min Range: -2.7716

Max Act: 2.4190. Min Act: -0.0000

Data Index: 1095950 (C4 (Web Text))

Max Activating Token Index: 705

Text #10

Max Range: 2.7716. Min Range: -2.7716

Max Act: 2.2652. Min Act: -0.0000

Data Index: 57027 (C4 (Web Text))

Max Activating Token Index: 771

Text #11

Max Range: 2.7716. Min Range: -2.7716

Max Act: 2.2580. Min Act: -0.0000

Data Index: 408554 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 2.7716. Min Range: -2.7716

Max Act: 2.3796. Min Act: -0.0000

Data Index: 784783 (C4 (Web Text))

Max Activating Token Index: 780

Text #13

Max Range: 2.7716. Min Range: -2.7716

Max Act: 2.2372. Min Act: -0.0000

Data Index: 390000 (C4 (Web Text))

Max Activating Token Index: 1005

Text #14

Max Range: 2.7716. Min Range: -2.7716

Max Act: 2.2343. Min Act: -0.0000

Data Index: 1281440 (C4 (Web Text))

Max Activating Token Index: 507

Text #15

Max Range: 2.7716. Min Range: -2.7716

Max Act: 2.1956. Min Act: -0.0000

Data Index: 836877 (C4 (Web Text))

Max Activating Token Index: 151

Text #16

Max Range: 2.7716. Min Range: -2.7716

Max Act: 2.0783. Min Act: -0.0000

Data Index: 203254 (C4 (Web Text))

Max Activating Token Index: 509

Text #17

Max Range: 2.7716. Min Range: -2.7716

Max Act: 2.2907. Min Act: -0.0000

Data Index: 1197545 (C4 (Web Text))

Max Activating Token Index: 568

Text #18

Max Range: 2.7716. Min Range: -2.7716

Max Act: 2.1606. Min Act: -0.0000

Data Index: 1007482 (C4 (Web Text))

Max Activating Token Index: 593

Text #19

Max Range: 2.7716. Min Range: -2.7716

Max Act: 2.1474. Min Act: -0.0000

Data Index: 944959 (C4 (Web Text))

Max Activating Token Index: 518