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

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

Neuron 4843 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: 11.3046. Min Range: -11.3046

Max Act: 11.1643. Min Act: -0.0000

Data Index: 1022761 (C4 (Web Text))

Max Activating Token Index: 874

Text #1

Max Range: 11.3046. Min Range: -11.3046

Max Act: 11.1662. Min Act: -0.0000

Data Index: 1032071 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 11.3046. Min Range: -11.3046

Max Act: 11.0771. Min Act: -0.0000

Data Index: 964499 (C4 (Web Text))

Max Activating Token Index: 620

Text #3

Max Range: 11.3046. Min Range: -11.3046

Max Act: 11.3046. Min Act: -0.0000

Data Index: 426431 (C4 (Web Text))

Max Activating Token Index: 649

Text #4

Max Range: 11.3046. Min Range: -11.3046

Max Act: 10.7226. Min Act: -0.0000

Data Index: 60871 (C4 (Web Text))

Max Activating Token Index: 283

Text #5

Max Range: 11.3046. Min Range: -11.3046

Max Act: 10.8579. Min Act: -0.0000

Data Index: 200453 (C4 (Web Text))

Max Activating Token Index: 158

Text #6

Max Range: 11.3046. Min Range: -11.3046

Max Act: 10.7026. Min Act: -0.0000

Data Index: 288483 (C4 (Web Text))

Max Activating Token Index: 524

Text #7

Max Range: 11.3046. Min Range: -11.3046

Max Act: 10.8190. Min Act: -0.0000

Data Index: 25070 (C4 (Web Text))

Max Activating Token Index: 174

Text #8

Max Range: 11.3046. Min Range: -11.3046

Max Act: 11.0257. Min Act: -0.0000

Data Index: 15858 (C4 (Web Text))

Max Activating Token Index: 655

Text #9

Max Range: 11.3046. Min Range: -11.3046

Max Act: 10.7535. Min Act: -0.0000

Data Index: 871854 (C4 (Web Text))

Max Activating Token Index: 114

Text #10

Max Range: 11.3046. Min Range: -11.3046

Max Act: 10.7107. Min Act: -0.0000

Data Index: 364538 (C4 (Web Text))

Max Activating Token Index: 665

Text #11

Max Range: 11.3046. Min Range: -11.3046

Max Act: 10.9333. Min Act: -0.0000

Data Index: 1312134 (C4 (Web Text))

Max Activating Token Index: 521

Text #12

Max Range: 11.3046. Min Range: -11.3046

Max Act: 10.9219. Min Act: -0.0000

Data Index: 456891 (C4 (Web Text))

Max Activating Token Index: 982

Text #13

Max Range: 11.3046. Min Range: -11.3046

Max Act: 10.6904. Min Act: -0.0000

Data Index: 1221248 (C4 (Web Text))

Max Activating Token Index: 775

Text #14

Max Range: 11.3046. Min Range: -11.3046

Max Act: 10.6659. Min Act: -0.0000

Data Index: 1010836 (C4 (Web Text))

Max Activating Token Index: 222

Text #15

Max Range: 11.3046. Min Range: -11.3046

Max Act: 10.6806. Min Act: -0.0000

Data Index: 1066141 (C4 (Web Text))

Max Activating Token Index: 426

Text #16

Max Range: 11.3046. Min Range: -11.3046

Max Act: 10.2314. Min Act: -0.0000

Data Index: 72967 (C4 (Web Text))

Max Activating Token Index: 884

Text #17

Max Range: 11.3046. Min Range: -11.3046

Max Act: 10.5795. Min Act: -0.0000

Data Index: 599049 (C4 (Web Text))

Max Activating Token Index: 445

Text #18

Max Range: 11.3046. Min Range: -11.3046

Max Act: 10.4416. Min Act: -0.0000

Data Index: 1352254 (C4 (Web Text))

Max Activating Token Index: 509

Text #19

Max Range: 11.3046. Min Range: -11.3046

Max Act: 10.6875. Min Act: -0.0000

Data Index: 979681 (C4 (Web Text))

Max Activating Token Index: 506