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

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

Neuron 3311 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8847. Min Range: -0.8847

Max Act: 0.8847. Min Act: -0.0000

Data Index: 1094987 (C4 (Web Text))

Max Activating Token Index: 657

Text #1

Max Range: 0.8847. Min Range: -0.8847

Max Act: 0.7814. Min Act: -0.0000

Data Index: 821938 (C4 (Web Text))

Max Activating Token Index: 986

Text #2

Max Range: 0.8847. Min Range: -0.8847

Max Act: 0.4629. Min Act: -0.0000

Data Index: 1238294 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 0.8847. Min Range: -0.8847

Max Act: 0.4094. Min Act: -0.0000

Data Index: 899051 (C4 (Web Text))

Max Activating Token Index: 224

Text #4

Max Range: 0.8847. Min Range: -0.8847

Max Act: 0.4028. Min Act: -0.0000

Data Index: 498201 (C4 (Web Text))

Max Activating Token Index: 537

Text #5

Max Range: 0.8847. Min Range: -0.8847

Max Act: 0.3883. Min Act: -0.0000

Data Index: 1313068 (C4 (Web Text))

Max Activating Token Index: 79

Text #6

Max Range: 0.8847. Min Range: -0.8847

Max Act: 0.3962. Min Act: -0.0000

Data Index: 2562 (C4 (Web Text))

Max Activating Token Index: 890

Text #7

Max Range: 0.8847. Min Range: -0.8847

Max Act: 0.4004. Min Act: -0.0000

Data Index: 239911 (C4 (Web Text))

Max Activating Token Index: 169

Text #8

Max Range: 0.8847. Min Range: -0.8847

Max Act: 0.4007. Min Act: -0.0000

Data Index: 724291 (C4 (Web Text))

Max Activating Token Index: 380

Text #9

Max Range: 0.8847. Min Range: -0.8847

Max Act: 0.3799. Min Act: -0.0000

Data Index: 534810 (C4 (Web Text))

Max Activating Token Index: 441

Text #10

Max Range: 0.8847. Min Range: -0.8847

Max Act: 0.3601. Min Act: -0.0000

Data Index: 196633 (C4 (Web Text))

Max Activating Token Index: 557

Text #11

Max Range: 0.8847. Min Range: -0.8847

Max Act: 0.3481. Min Act: -0.0000

Data Index: 901649 (C4 (Web Text))

Max Activating Token Index: 380

Text #12

Max Range: 0.8847. Min Range: -0.8847

Max Act: 0.3497. Min Act: -0.0000

Data Index: 249991 (C4 (Web Text))

Max Activating Token Index: 161

Text #13

Max Range: 0.8847. Min Range: -0.8847

Max Act: 0.3396. Min Act: -0.0000

Data Index: 961876 (C4 (Web Text))

Max Activating Token Index: 859

Text #14

Max Range: 0.8847. Min Range: -0.8847

Max Act: 0.3419. Min Act: -0.0000

Data Index: 234969 (C4 (Web Text))

Max Activating Token Index: 528

Text #15

Max Range: 0.8847. Min Range: -0.8847

Max Act: 0.3366. Min Act: -0.0000

Data Index: 708733 (C4 (Web Text))

Max Activating Token Index: 896

Text #16

Max Range: 0.8847. Min Range: -0.8847

Max Act: 0.3105. Min Act: -0.0000

Data Index: 896512 (C4 (Web Text))

Max Activating Token Index: 498

Text #17

Max Range: 0.8847. Min Range: -0.8847

Max Act: 0.3084. Min Act: -0.0000

Data Index: 890391 (C4 (Web Text))

Max Activating Token Index: 836

Text #18

Max Range: 0.8847. Min Range: -0.8847

Max Act: 0.2998. Min Act: -0.0000

Data Index: 237876 (C4 (Web Text))

Max Activating Token Index: 801

Text #19

Max Range: 0.8847. Min Range: -0.8847

Max Act: 0.3123. Min Act: -0.0000

Data Index: 505720 (C4 (Web Text))

Max Activating Token Index: 358