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

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

Neuron 240 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: 0.7254. Min Range: -0.7254

Max Act: 0.7254. Min Act: -0.0002

Data Index: 717080 (C4 (Web Text))

Max Activating Token Index: 762

Text #1

Max Range: 0.7254. Min Range: -0.7254

Max Act: 0.7218. Min Act: -0.0002

Data Index: 929704 (C4 (Web Text))

Max Activating Token Index: 902

Text #2

Max Range: 0.7254. Min Range: -0.7254

Max Act: 0.7241. Min Act: -0.0002

Data Index: 417145 (C4 (Web Text))

Max Activating Token Index: 664

Text #3

Max Range: 0.7254. Min Range: -0.7254

Max Act: 0.7040. Min Act: -0.0002

Data Index: 199612 (C4 (Web Text))

Max Activating Token Index: 208

Text #4

Max Range: 0.7254. Min Range: -0.7254

Max Act: 0.6954. Min Act: -0.0002

Data Index: 36144 (C4 (Web Text))

Max Activating Token Index: 873

Text #5

Max Range: 0.7254. Min Range: -0.7254

Max Act: 0.6947. Min Act: -0.0002

Data Index: 61900 (C4 (Web Text))

Max Activating Token Index: 528

Text #6

Max Range: 0.7254. Min Range: -0.7254

Max Act: 0.6828. Min Act: -0.0002

Data Index: 1209990 (C4 (Web Text))

Max Activating Token Index: 347

Text #7

Max Range: 0.7254. Min Range: -0.7254

Max Act: 0.6821. Min Act: -0.0002

Data Index: 779818 (C4 (Web Text))

Max Activating Token Index: 39

Text #8

Max Range: 0.7254. Min Range: -0.7254

Max Act: 0.6791. Min Act: -0.0002

Data Index: 599118 (C4 (Web Text))

Max Activating Token Index: 4

Text #9

Max Range: 0.7254. Min Range: -0.7254

Max Act: 0.6760. Min Act: -0.0002

Data Index: 855835 (C4 (Web Text))

Max Activating Token Index: 707

Text #10

Max Range: 0.7254. Min Range: -0.7254

Max Act: 0.6753. Min Act: -0.0002

Data Index: 826014 (C4 (Web Text))

Max Activating Token Index: 2

Text #11

Max Range: 0.7254. Min Range: -0.7254

Max Act: 0.6789. Min Act: -0.0002

Data Index: 447303 (C4 (Web Text))

Max Activating Token Index: 252

Text #12

Max Range: 0.7254. Min Range: -0.7254

Max Act: 0.6627. Min Act: -0.0003

Data Index: 833066 (C4 (Web Text))

Max Activating Token Index: 262

Text #13

Max Range: 0.7254. Min Range: -0.7254

Max Act: 0.6545. Min Act: -0.0002

Data Index: 1079965 (C4 (Web Text))

Max Activating Token Index: 388

Text #14

Max Range: 0.7254. Min Range: -0.7254

Max Act: 0.6470. Min Act: -0.0002

Data Index: 953311 (C4 (Web Text))

Max Activating Token Index: 481

Text #15

Max Range: 0.7254. Min Range: -0.7254

Max Act: 0.6562. Min Act: -0.0002

Data Index: 849830 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 0.7254. Min Range: -0.7254

Max Act: 0.6492. Min Act: -0.0002

Data Index: 800581 (C4 (Web Text))

Max Activating Token Index: 854

Text #17

Max Range: 0.7254. Min Range: -0.7254

Max Act: 0.6592. Min Act: -0.0002

Data Index: 90575 (C4 (Web Text))

Max Activating Token Index: 925

Text #18

Max Range: 0.7254. Min Range: -0.7254

Max Act: 0.6491. Min Act: -0.0002

Data Index: 249237 (C4 (Web Text))

Max Activating Token Index: 308

Text #19

Max Range: 0.7254. Min Range: -0.7254

Max Act: 0.6315. Min Act: -0.0003

Data Index: 578153 (C4 (Web Text))

Max Activating Token Index: 404