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

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

Neuron 2086 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: 4.1986. Min Range: -4.1986

Max Act: 4.1917. Min Act: -0.0000

Data Index: 1025897 (C4 (Web Text))

Max Activating Token Index: 984

Text #1

Max Range: 4.1986. Min Range: -4.1986

Max Act: 4.1986. Min Act: -0.0000

Data Index: 1022202 (C4 (Web Text))

Max Activating Token Index: 901

Text #2

Max Range: 4.1986. Min Range: -4.1986

Max Act: 4.0033. Min Act: -0.0000

Data Index: 1143512 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 4.1986. Min Range: -4.1986

Max Act: 3.9675. Min Act: -0.0000

Data Index: 1004175 (C4 (Web Text))

Max Activating Token Index: 116

Text #4

Max Range: 4.1986. Min Range: -4.1986

Max Act: 3.8672. Min Act: -0.0000

Data Index: 1097424 (C4 (Web Text))

Max Activating Token Index: 960

Text #5

Max Range: 4.1986. Min Range: -4.1986

Max Act: 3.5900. Min Act: -0.0000

Data Index: 1164053 (C4 (Web Text))

Max Activating Token Index: 346

Text #6

Max Range: 4.1986. Min Range: -4.1986

Max Act: 3.8954. Min Act: -0.0000

Data Index: 1282451 (C4 (Web Text))

Max Activating Token Index: 424

Text #7

Max Range: 4.1986. Min Range: -4.1986

Max Act: 3.7248. Min Act: -0.0000

Data Index: 143644 (C4 (Web Text))

Max Activating Token Index: 629

Text #8

Max Range: 4.1986. Min Range: -4.1986

Max Act: 3.5541. Min Act: -0.0000

Data Index: 949999 (C4 (Web Text))

Max Activating Token Index: 812

Text #9

Max Range: 4.1986. Min Range: -4.1986

Max Act: 3.8479. Min Act: -0.0000

Data Index: 292313 (C4 (Web Text))

Max Activating Token Index: 950

Text #10

Max Range: 4.1986. Min Range: -4.1986

Max Act: 3.5475. Min Act: -0.0000

Data Index: 1173322 (C4 (Web Text))

Max Activating Token Index: 392

Text #11

Max Range: 4.1986. Min Range: -4.1986

Max Act: 3.6478. Min Act: -0.0000

Data Index: 905323 (C4 (Web Text))

Max Activating Token Index: 278

Text #12

Max Range: 4.1986. Min Range: -4.1986

Max Act: 3.8083. Min Act: -0.0000

Data Index: 754581 (C4 (Web Text))

Max Activating Token Index: 415

Text #13

Max Range: 4.1986. Min Range: -4.1986

Max Act: 3.6169. Min Act: -0.0000

Data Index: 354786 (C4 (Web Text))

Max Activating Token Index: 153

Text #14

Max Range: 4.1986. Min Range: -4.1986

Max Act: 3.5868. Min Act: -0.0000

Data Index: 809019 (C4 (Web Text))

Max Activating Token Index: 776

Text #15

Max Range: 4.1986. Min Range: -4.1986

Max Act: 3.7139. Min Act: -0.0000

Data Index: 916517 (C4 (Web Text))

Max Activating Token Index: 667

Text #16

Max Range: 4.1986. Min Range: -4.1986

Max Act: 3.5673. Min Act: 0.0000

Data Index: 214192 (C4 (Web Text))

Max Activating Token Index: 610

Text #17

Max Range: 4.1986. Min Range: -4.1986

Max Act: 3.4108. Min Act: -0.0000

Data Index: 524423 (C4 (Web Text))

Max Activating Token Index: 789

Text #18

Max Range: 4.1986. Min Range: -4.1986

Max Act: 3.5229. Min Act: -0.0000

Data Index: 1175779 (C4 (Web Text))

Max Activating Token Index: 628

Text #19

Max Range: 4.1986. Min Range: -4.1986

Max Act: 3.6443. Min Act: -0.0000

Data Index: 123474 (C4 (Web Text))

Max Activating Token Index: 723