Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 725 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.5988. Min Act: -0.0001

Data Index: 888092 (C4 (Web Text))

Max Activating Token Index: 551

Text #1

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.5649. Min Act: -0.0001

Data Index: 662300 (C4 (Web Text))

Max Activating Token Index: 439

Text #2

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.5750. Min Act: -0.0001

Data Index: 986249 (C4 (Web Text))

Max Activating Token Index: 143

Text #3

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.5806. Min Act: -0.0001

Data Index: 494502 (C4 (Web Text))

Max Activating Token Index: 880

Text #4

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.5403. Min Act: -0.0001

Data Index: 990517 (C4 (Web Text))

Max Activating Token Index: 18

Text #5

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.5332. Min Act: -0.0001

Data Index: 978534 (C4 (Web Text))

Max Activating Token Index: 585

Text #6

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.5267. Min Act: -0.0001

Data Index: 505519 (C4 (Web Text))

Max Activating Token Index: 568

Text #7

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.5069. Min Act: -0.0000

Data Index: 863780 (C4 (Web Text))

Max Activating Token Index: 298

Text #8

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.5103. Min Act: -0.0001

Data Index: 1135238 (C4 (Web Text))

Max Activating Token Index: 505

Text #9

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.5225. Min Act: -0.0001

Data Index: 268117 (C4 (Web Text))

Max Activating Token Index: 433

Text #10

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.5358. Min Act: -0.0000

Data Index: 619206 (C4 (Web Text))

Max Activating Token Index: 670

Text #11

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4685. Min Act: -0.0001

Data Index: 763373 (C4 (Web Text))

Max Activating Token Index: 252

Text #12

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4931. Min Act: -0.0001

Data Index: 632761 (C4 (Web Text))

Max Activating Token Index: 136

Text #13

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4697. Min Act: -0.0001

Data Index: 1125555 (C4 (Web Text))

Max Activating Token Index: 505

Text #14

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4829. Min Act: -0.0001

Data Index: 1238454 (C4 (Web Text))

Max Activating Token Index: 69

Text #15

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4628. Min Act: -0.0001

Data Index: 1060215 (C4 (Web Text))

Max Activating Token Index: 103

Text #16

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4456. Min Act: -0.0001

Data Index: 567274 (C4 (Web Text))

Max Activating Token Index: 311

Text #17

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4616. Min Act: -0.0001

Data Index: 560714 (C4 (Web Text))

Max Activating Token Index: 575

Text #18

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4628. Min Act: -0.0001

Data Index: 252340 (C4 (Web Text))

Max Activating Token Index: 100

Text #19

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4467. Min Act: -0.0001

Data Index: 906975 (C4 (Web Text))

Max Activating Token Index: 591