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

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

Neuron 5333 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5975. Min Range: -2.5975

Max Act: 2.5975. Min Act: 0.0000

Data Index: 1128933 (C4 (Web Text))

Max Activating Token Index: 755

Text #1

Max Range: 2.5975. Min Range: -2.5975

Max Act: 2.0878. Min Act: 0.0000

Data Index: 399405 (C4 (Web Text))

Max Activating Token Index: 930

Text #2

Max Range: 2.5975. Min Range: -2.5975

Max Act: 1.8410. Min Act: -0.0000

Data Index: 162865 (C4 (Web Text))

Max Activating Token Index: 549

Text #3

Max Range: 2.5975. Min Range: -2.5975

Max Act: 1.6824. Min Act: -0.0000

Data Index: 959547 (C4 (Web Text))

Max Activating Token Index: 384

Text #4

Max Range: 2.5975. Min Range: -2.5975

Max Act: 1.6482. Min Act: -0.0000

Data Index: 500873 (C4 (Web Text))

Max Activating Token Index: 938

Text #5

Max Range: 2.5975. Min Range: -2.5975

Max Act: 1.5825. Min Act: -0.0000

Data Index: 214315 (C4 (Web Text))

Max Activating Token Index: 330

Text #6

Max Range: 2.5975. Min Range: -2.5975

Max Act: 1.5766. Min Act: -0.0000

Data Index: 1116629 (C4 (Web Text))

Max Activating Token Index: 607

Text #7

Max Range: 2.5975. Min Range: -2.5975

Max Act: 1.6421. Min Act: -0.0000

Data Index: 1200006 (C4 (Web Text))

Max Activating Token Index: 279

Text #8

Max Range: 2.5975. Min Range: -2.5975

Max Act: 1.5573. Min Act: -0.0000

Data Index: 233587 (C4 (Web Text))

Max Activating Token Index: 255

Text #9

Max Range: 2.5975. Min Range: -2.5975

Max Act: 1.4528. Min Act: -0.0000

Data Index: 713432 (C4 (Web Text))

Max Activating Token Index: 466

Text #10

Max Range: 2.5975. Min Range: -2.5975

Max Act: 1.4964. Min Act: -0.0000

Data Index: 511912 (C4 (Web Text))

Max Activating Token Index: 105

Text #11

Max Range: 2.5975. Min Range: -2.5975

Max Act: 1.3998. Min Act: -0.0000

Data Index: 694745 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 2.5975. Min Range: -2.5975

Max Act: 1.4785. Min Act: -0.0000

Data Index: 488710 (C4 (Web Text))

Max Activating Token Index: 604

Text #13

Max Range: 2.5975. Min Range: -2.5975

Max Act: 1.4667. Min Act: 0.0001

Data Index: 247741 (C4 (Web Text))

Max Activating Token Index: 738

Text #14

Max Range: 2.5975. Min Range: -2.5975

Max Act: 1.4671. Min Act: -0.0000

Data Index: 994491 (C4 (Web Text))

Max Activating Token Index: 431

Text #15

Max Range: 2.5975. Min Range: -2.5975

Max Act: 1.4565. Min Act: -0.0000

Data Index: 513050 (C4 (Web Text))

Max Activating Token Index: 205

Text #16

Max Range: 2.5975. Min Range: -2.5975

Max Act: 1.3701. Min Act: 0.0000

Data Index: 368228 (C4 (Web Text))

Max Activating Token Index: 316

Text #17

Max Range: 2.5975. Min Range: -2.5975

Max Act: 1.5310. Min Act: -0.0000

Data Index: 739816 (C4 (Web Text))

Max Activating Token Index: 352

Text #18

Max Range: 2.5975. Min Range: -2.5975

Max Act: 1.3530. Min Act: -0.0000

Data Index: 596081 (C4 (Web Text))

Max Activating Token Index: 205

Text #19

Max Range: 2.5975. Min Range: -2.5975

Max Act: 1.3462. Min Act: -0.0000

Data Index: 895863 (C4 (Web Text))

Max Activating Token Index: 418