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

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

Neuron 1070 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: 0.2951. Min Range: -0.2951

Max Act: 0.2951. Min Act: -0.0003

Data Index: 133205 (C4 (Web Text))

Max Activating Token Index: 629

Text #1

Max Range: 0.2951. Min Range: -0.2951

Max Act: 0.2683. Min Act: -0.0002

Data Index: 546932 (C4 (Web Text))

Max Activating Token Index: 134

Text #2

Max Range: 0.2951. Min Range: -0.2951

Max Act: 0.2649. Min Act: -0.0002

Data Index: 1182128 (C4 (Web Text))

Max Activating Token Index: 122

Text #3

Max Range: 0.2951. Min Range: -0.2951

Max Act: 0.2629. Min Act: -0.0002

Data Index: 748646 (C4 (Web Text))

Max Activating Token Index: 107

Text #4

Max Range: 0.2951. Min Range: -0.2951

Max Act: 0.2587. Min Act: -0.0002

Data Index: 1004316 (C4 (Web Text))

Max Activating Token Index: 252

Text #5

Max Range: 0.2951. Min Range: -0.2951

Max Act: 0.2494. Min Act: -0.0002

Data Index: 365855 (C4 (Web Text))

Max Activating Token Index: 92

Text #6

Max Range: 0.2951. Min Range: -0.2951

Max Act: 0.2432. Min Act: -0.0002

Data Index: 726975 (C4 (Web Text))

Max Activating Token Index: 116

Text #7

Max Range: 0.2951. Min Range: -0.2951

Max Act: 0.2438. Min Act: -0.0002

Data Index: 503424 (C4 (Web Text))

Max Activating Token Index: 107

Text #8

Max Range: 0.2951. Min Range: -0.2951

Max Act: 0.2410. Min Act: -0.0002

Data Index: 683296 (C4 (Web Text))

Max Activating Token Index: 226

Text #9

Max Range: 0.2951. Min Range: -0.2951

Max Act: 0.2434. Min Act: -0.0002

Data Index: 640995 (C4 (Web Text))

Max Activating Token Index: 102

Text #10

Max Range: 0.2951. Min Range: -0.2951

Max Act: 0.2490. Min Act: -0.0002

Data Index: 534496 (C4 (Web Text))

Max Activating Token Index: 120

Text #11

Max Range: 0.2951. Min Range: -0.2951

Max Act: 0.2370. Min Act: -0.0002

Data Index: 1193237 (C4 (Web Text))

Max Activating Token Index: 111

Text #12

Max Range: 0.2951. Min Range: -0.2951

Max Act: 0.2434. Min Act: -0.0002

Data Index: 582376 (C4 (Web Text))

Max Activating Token Index: 14

Text #13

Max Range: 0.2951. Min Range: -0.2951

Max Act: 0.2458. Min Act: -0.0002

Data Index: 662325 (C4 (Web Text))

Max Activating Token Index: 12

Text #14

Max Range: 0.2951. Min Range: -0.2951

Max Act: 0.2442. Min Act: -0.0002

Data Index: 1312054 (C4 (Web Text))

Max Activating Token Index: 266

Text #15

Max Range: 0.2951. Min Range: -0.2951

Max Act: 0.2370. Min Act: -0.0002

Data Index: 13173 (C4 (Web Text))

Max Activating Token Index: 819

Text #16

Max Range: 0.2951. Min Range: -0.2951

Max Act: 0.2378. Min Act: -0.0002

Data Index: 103428 (C4 (Web Text))

Max Activating Token Index: 191

Text #17

Max Range: 0.2951. Min Range: -0.2951

Max Act: 0.2340. Min Act: -0.0002

Data Index: 1082290 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 0.2951. Min Range: -0.2951

Max Act: 0.2346. Min Act: -0.0002

Data Index: 37546 (C4 (Web Text))

Max Activating Token Index: 51

Text #19

Max Range: 0.2951. Min Range: -0.2951

Max Act: 0.2327. Min Act: -0.0002

Data Index: 1158099 (C4 (Web Text))

Max Activating Token Index: 99