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

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

Neuron 114 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4918. Min Range: -0.4918

Max Act: 0.4918. Min Act: -0.0000

Data Index: 363682 (C4 (Web Text))

Max Activating Token Index: 432

Text #1

Max Range: 0.4918. Min Range: -0.4918

Max Act: 0.4437. Min Act: -0.0000

Data Index: 453025 (C4 (Web Text))

Max Activating Token Index: 66

Text #2

Max Range: 0.4918. Min Range: -0.4918

Max Act: 0.4474. Min Act: -0.0000

Data Index: 252174 (C4 (Web Text))

Max Activating Token Index: 652

Text #3

Max Range: 0.4918. Min Range: -0.4918

Max Act: 0.3859. Min Act: -0.0000

Data Index: 1286576 (C4 (Web Text))

Max Activating Token Index: 797

Text #4

Max Range: 0.4918. Min Range: -0.4918

Max Act: 0.4309. Min Act: -0.0000

Data Index: 1288069 (C4 (Web Text))

Max Activating Token Index: 551

Text #5

Max Range: 0.4918. Min Range: -0.4918

Max Act: 0.4106. Min Act: -0.0000

Data Index: 731231 (C4 (Web Text))

Max Activating Token Index: 487

Text #6

Max Range: 0.4918. Min Range: -0.4918

Max Act: 0.4199. Min Act: -0.0000

Data Index: 1240359 (C4 (Web Text))

Max Activating Token Index: 790

Text #7

Max Range: 0.4918. Min Range: -0.4918

Max Act: 0.4171. Min Act: -0.0000

Data Index: 588667 (C4 (Web Text))

Max Activating Token Index: 764

Text #8

Max Range: 0.4918. Min Range: -0.4918

Max Act: 0.3925. Min Act: -0.0000

Data Index: 809738 (C4 (Web Text))

Max Activating Token Index: 838

Text #9

Max Range: 0.4918. Min Range: -0.4918

Max Act: 0.3933. Min Act: -0.0000

Data Index: 1231190 (C4 (Web Text))

Max Activating Token Index: 139

Text #10

Max Range: 0.4918. Min Range: -0.4918

Max Act: 0.3873. Min Act: -0.0000

Data Index: 781036 (C4 (Web Text))

Max Activating Token Index: 568

Text #11

Max Range: 0.4918. Min Range: -0.4918

Max Act: 0.3691. Min Act: -0.0000

Data Index: 1111567 (C4 (Web Text))

Max Activating Token Index: 390

Text #12

Max Range: 0.4918. Min Range: -0.4918

Max Act: 0.3807. Min Act: -0.0000

Data Index: 1334656 (C4 (Web Text))

Max Activating Token Index: 345

Text #13

Max Range: 0.4918. Min Range: -0.4918

Max Act: 0.3592. Min Act: -0.0000

Data Index: 75549 (C4 (Web Text))

Max Activating Token Index: 773

Text #14

Max Range: 0.4918. Min Range: -0.4918

Max Act: 0.3745. Min Act: -0.0000

Data Index: 621887 (C4 (Web Text))

Max Activating Token Index: 826

Text #15

Max Range: 0.4918. Min Range: -0.4918

Max Act: 0.3740. Min Act: -0.0000

Data Index: 1214162 (C4 (Web Text))

Max Activating Token Index: 962

Text #16

Max Range: 0.4918. Min Range: -0.4918

Max Act: 0.3580. Min Act: -0.0000

Data Index: 183740 (C4 (Web Text))

Max Activating Token Index: 82

Text #17

Max Range: 0.4918. Min Range: -0.4918

Max Act: 0.4038. Min Act: -0.0000

Data Index: 641748 (C4 (Web Text))

Max Activating Token Index: 986

Text #18

Max Range: 0.4918. Min Range: -0.4918

Max Act: 0.3660. Min Act: -0.0000

Data Index: 179744 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 0.4918. Min Range: -0.4918

Max Act: 0.3683. Min Act: -0.0000

Data Index: 1119200 (C4 (Web Text))

Max Activating Token Index: 578