Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2996 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.7071. Min Act: -0.0000

Data Index: 189969 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.6926. Min Act: -0.0000

Data Index: 390495 (C4 (Web Text))

Max Activating Token Index: 832

Text #2

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.6845. Min Act: -0.0000

Data Index: 596283 (C4 (Web Text))

Max Activating Token Index: 382

Text #3

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.6346. Min Act: -0.0000

Data Index: 1109057 (C4 (Web Text))

Max Activating Token Index: 886

Text #4

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.6294. Min Act: -0.0000

Data Index: 764579 (C4 (Web Text))

Max Activating Token Index: 383

Text #5

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.6327. Min Act: -0.0000

Data Index: 532868 (C4 (Web Text))

Max Activating Token Index: 176

Text #6

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.5739. Min Act: -0.0000

Data Index: 1003745 (C4 (Web Text))

Max Activating Token Index: 867

Text #7

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.5681. Min Act: -0.0000

Data Index: 640239 (C4 (Web Text))

Max Activating Token Index: 588

Text #8

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.4763. Min Act: -0.0000

Data Index: 1023758 (C4 (Web Text))

Max Activating Token Index: 429

Text #9

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.4368. Min Act: -0.0000

Data Index: 1053948 (C4 (Web Text))

Max Activating Token Index: 716

Text #10

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.4363. Min Act: -0.0000

Data Index: 912409 (C4 (Web Text))

Max Activating Token Index: 469

Text #11

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.4609. Min Act: -0.0000

Data Index: 668439 (C4 (Web Text))

Max Activating Token Index: 842

Text #12

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.4750. Min Act: 0.0000

Data Index: 1002249 (C4 (Web Text))

Max Activating Token Index: 120

Text #13

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.4318. Min Act: -0.0000

Data Index: 1011394 (C4 (Web Text))

Max Activating Token Index: 110

Text #14

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.4334. Min Act: -0.0000

Data Index: 349737 (C4 (Web Text))

Max Activating Token Index: 270

Text #15

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.4293. Min Act: -0.0000

Data Index: 983944 (C4 (Web Text))

Max Activating Token Index: 872

Text #16

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.3906. Min Act: -0.0000

Data Index: 466054 (C4 (Web Text))

Max Activating Token Index: 195

Text #17

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.4454. Min Act: -0.0000

Data Index: 107776 (C4 (Web Text))

Max Activating Token Index: 270

Text #18

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.4095. Min Act: -0.0000

Data Index: 859051 (C4 (Web Text))

Max Activating Token Index: 230

Text #19

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.3967. Min Act: -0.0000

Data Index: 901583 (C4 (Web Text))

Max Activating Token Index: 487