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

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

Neuron 1992 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.8586. Min Range: -0.8586

Max Act: 0.8586. Min Act: -0.0002

Data Index: 717667 (C4 (Web Text))

Max Activating Token Index: 770

Text #1

Max Range: 0.8586. Min Range: -0.8586

Max Act: 0.8171. Min Act: -0.0003

Data Index: 524359 (C4 (Web Text))

Max Activating Token Index: 661

Text #2

Max Range: 0.8586. Min Range: -0.8586

Max Act: 0.8326. Min Act: -0.0002

Data Index: 371046 (C4 (Web Text))

Max Activating Token Index: 16

Text #3

Max Range: 0.8586. Min Range: -0.8586

Max Act: 0.8318. Min Act: -0.0002

Data Index: 836379 (C4 (Web Text))

Max Activating Token Index: 92

Text #4

Max Range: 0.8586. Min Range: -0.8586

Max Act: 0.8132. Min Act: -0.0002

Data Index: 246997 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 0.8586. Min Range: -0.8586

Max Act: 0.7899. Min Act: -0.0002

Data Index: 1162081 (C4 (Web Text))

Max Activating Token Index: 771

Text #6

Max Range: 0.8586. Min Range: -0.8586

Max Act: 0.8032. Min Act: -0.0003

Data Index: 805163 (C4 (Web Text))

Max Activating Token Index: 44

Text #7

Max Range: 0.8586. Min Range: -0.8586

Max Act: 0.7894. Min Act: -0.0002

Data Index: 1033567 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 0.8586. Min Range: -0.8586

Max Act: 0.7817. Min Act: -0.0002

Data Index: 535637 (C4 (Web Text))

Max Activating Token Index: 51

Text #9

Max Range: 0.8586. Min Range: -0.8586

Max Act: 0.7816. Min Act: -0.0003

Data Index: 598838 (C4 (Web Text))

Max Activating Token Index: 123

Text #10

Max Range: 0.8586. Min Range: -0.8586

Max Act: 0.8027. Min Act: -0.0002

Data Index: 715199 (C4 (Web Text))

Max Activating Token Index: 33

Text #11

Max Range: 0.8586. Min Range: -0.8586

Max Act: 0.7735. Min Act: -0.0002

Data Index: 1144154 (C4 (Web Text))

Max Activating Token Index: 250

Text #12

Max Range: 0.8586. Min Range: -0.8586

Max Act: 0.7800. Min Act: -0.0003

Data Index: 954272 (C4 (Web Text))

Max Activating Token Index: 12

Text #13

Max Range: 0.8586. Min Range: -0.8586

Max Act: 0.7634. Min Act: -0.0002

Data Index: 79400 (C4 (Web Text))

Max Activating Token Index: 70

Text #14

Max Range: 0.8586. Min Range: -0.8586

Max Act: 0.7550. Min Act: -0.0002

Data Index: 11063 (C4 (Web Text))

Max Activating Token Index: 275

Text #15

Max Range: 0.8586. Min Range: -0.8586

Max Act: 0.7691. Min Act: -0.0002

Data Index: 679740 (C4 (Web Text))

Max Activating Token Index: 280

Text #16

Max Range: 0.8586. Min Range: -0.8586

Max Act: 0.7677. Min Act: -0.0002

Data Index: 437125 (C4 (Web Text))

Max Activating Token Index: 175

Text #17

Max Range: 0.8586. Min Range: -0.8586

Max Act: 0.7701. Min Act: -0.0002

Data Index: 752887 (C4 (Web Text))

Max Activating Token Index: 189

Text #18

Max Range: 0.8586. Min Range: -0.8586

Max Act: 0.7614. Min Act: -0.0003

Data Index: 254332 (C4 (Web Text))

Max Activating Token Index: 14

Text #19

Max Range: 0.8586. Min Range: -0.8586

Max Act: 0.7531. Min Act: -0.0002

Data Index: 1203148 (C4 (Web Text))

Max Activating Token Index: 308