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

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

Neuron 3505 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: 0.7384. Min Range: -0.7384

Max Act: 0.7384. Min Act: -0.0000

Data Index: 799983 (C4 (Web Text))

Max Activating Token Index: 460

Text #1

Max Range: 0.7384. Min Range: -0.7384

Max Act: 0.5453. Min Act: -0.0000

Data Index: 803917 (C4 (Web Text))

Max Activating Token Index: 40

Text #2

Max Range: 0.7384. Min Range: -0.7384

Max Act: 0.5218. Min Act: -0.0000

Data Index: 485706 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 0.7384. Min Range: -0.7384

Max Act: 0.4527. Min Act: -0.0000

Data Index: 1026424 (C4 (Web Text))

Max Activating Token Index: 526

Text #4

Max Range: 0.7384. Min Range: -0.7384

Max Act: 0.4382. Min Act: -0.0000

Data Index: 33223 (C4 (Web Text))

Max Activating Token Index: 862

Text #5

Max Range: 0.7384. Min Range: -0.7384

Max Act: 0.4147. Min Act: -0.0000

Data Index: 334322 (C4 (Web Text))

Max Activating Token Index: 727

Text #6

Max Range: 0.7384. Min Range: -0.7384

Max Act: 0.3960. Min Act: -0.0000

Data Index: 708705 (C4 (Web Text))

Max Activating Token Index: 28

Text #7

Max Range: 0.7384. Min Range: -0.7384

Max Act: 0.3982. Min Act: -0.0000

Data Index: 408358 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 0.7384. Min Range: -0.7384

Max Act: 0.3980. Min Act: -0.0000

Data Index: 1323995 (C4 (Web Text))

Max Activating Token Index: 1013

Text #9

Max Range: 0.7384. Min Range: -0.7384

Max Act: 0.3888. Min Act: -0.0000

Data Index: 313746 (C4 (Web Text))

Max Activating Token Index: 534

Text #10

Max Range: 0.7384. Min Range: -0.7384

Max Act: 0.3855. Min Act: -0.0000

Data Index: 380971 (C4 (Web Text))

Max Activating Token Index: 330

Text #11

Max Range: 0.7384. Min Range: -0.7384

Max Act: 0.3839. Min Act: -0.0000

Data Index: 947861 (C4 (Web Text))

Max Activating Token Index: 493

Text #12

Max Range: 0.7384. Min Range: -0.7384

Max Act: 0.3814. Min Act: -0.0000

Data Index: 864499 (C4 (Web Text))

Max Activating Token Index: 310

Text #13

Max Range: 0.7384. Min Range: -0.7384

Max Act: 0.3915. Min Act: -0.0000

Data Index: 1323256 (C4 (Web Text))

Max Activating Token Index: 398

Text #14

Max Range: 0.7384. Min Range: -0.7384

Max Act: 0.3749. Min Act: -0.0000

Data Index: 512986 (C4 (Web Text))

Max Activating Token Index: 301

Text #15

Max Range: 0.7384. Min Range: -0.7384

Max Act: 0.3673. Min Act: -0.0000

Data Index: 790132 (C4 (Web Text))

Max Activating Token Index: 924

Text #16

Max Range: 0.7384. Min Range: -0.7384

Max Act: 0.3618. Min Act: -0.0000

Data Index: 948835 (C4 (Web Text))

Max Activating Token Index: 284

Text #17

Max Range: 0.7384. Min Range: -0.7384

Max Act: 0.3638. Min Act: -0.0000

Data Index: 513477 (C4 (Web Text))

Max Activating Token Index: 774

Text #18

Max Range: 0.7384. Min Range: -0.7384

Max Act: 0.3608. Min Act: -0.0000

Data Index: 40407 (C4 (Web Text))

Max Activating Token Index: 92

Text #19

Max Range: 0.7384. Min Range: -0.7384

Max Act: 0.3348. Min Act: -0.0000

Data Index: 125748 (C4 (Web Text))

Max Activating Token Index: 881