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

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

Neuron 2718 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: 3.6522. Min Range: -3.6522

Max Act: 3.6522. Min Act: -0.0002

Data Index: 347425 (C4 (Web Text))

Max Activating Token Index: 51

Text #1

Max Range: 3.6522. Min Range: -3.6522

Max Act: 3.4481. Min Act: -0.0002

Data Index: 731986 (C4 (Web Text))

Max Activating Token Index: 23

Text #2

Max Range: 3.6522. Min Range: -3.6522

Max Act: 3.3714. Min Act: -0.0002

Data Index: 335565 (C4 (Web Text))

Max Activating Token Index: 195

Text #3

Max Range: 3.6522. Min Range: -3.6522

Max Act: 3.3726. Min Act: -0.0002

Data Index: 131202 (C4 (Web Text))

Max Activating Token Index: 195

Text #4

Max Range: 3.6522. Min Range: -3.6522

Max Act: 3.2780. Min Act: -0.0002

Data Index: 394633 (C4 (Web Text))

Max Activating Token Index: 198

Text #5

Max Range: 3.6522. Min Range: -3.6522

Max Act: 3.2689. Min Act: -0.0002

Data Index: 900010 (C4 (Web Text))

Max Activating Token Index: 183

Text #6

Max Range: 3.6522. Min Range: -3.6522

Max Act: 3.3581. Min Act: -0.0002

Data Index: 1289578 (C4 (Web Text))

Max Activating Token Index: 153

Text #7

Max Range: 3.6522. Min Range: -3.6522

Max Act: 3.2458. Min Act: -0.0002

Data Index: 1336797 (C4 (Web Text))

Max Activating Token Index: 130

Text #8

Max Range: 3.6522. Min Range: -3.6522

Max Act: 3.3167. Min Act: -0.0002

Data Index: 710919 (C4 (Web Text))

Max Activating Token Index: 322

Text #9

Max Range: 3.6522. Min Range: -3.6522

Max Act: 3.2638. Min Act: -0.0002

Data Index: 567052 (C4 (Web Text))

Max Activating Token Index: 499

Text #10

Max Range: 3.6522. Min Range: -3.6522

Max Act: 3.3113. Min Act: -0.0002

Data Index: 794414 (C4 (Web Text))

Max Activating Token Index: 401

Text #11

Max Range: 3.6522. Min Range: -3.6522

Max Act: 3.2550. Min Act: -0.0002

Data Index: 219972 (C4 (Web Text))

Max Activating Token Index: 174

Text #12

Max Range: 3.6522. Min Range: -3.6522

Max Act: 3.2708. Min Act: -0.0002

Data Index: 464553 (C4 (Web Text))

Max Activating Token Index: 289

Text #13

Max Range: 3.6522. Min Range: -3.6522

Max Act: 3.1228. Min Act: -0.0002

Data Index: 819326 (C4 (Web Text))

Max Activating Token Index: 764

Text #14

Max Range: 3.6522. Min Range: -3.6522

Max Act: 3.1948. Min Act: -0.0002

Data Index: 97727 (C4 (Web Text))

Max Activating Token Index: 227

Text #15

Max Range: 3.6522. Min Range: -3.6522

Max Act: 3.1862. Min Act: -0.0002

Data Index: 962789 (C4 (Web Text))

Max Activating Token Index: 649

Text #16

Max Range: 3.6522. Min Range: -3.6522

Max Act: 3.1917. Min Act: -0.0002

Data Index: 697324 (C4 (Web Text))

Max Activating Token Index: 468

Text #17

Max Range: 3.6522. Min Range: -3.6522

Max Act: 3.1965. Min Act: -0.0002

Data Index: 631538 (C4 (Web Text))

Max Activating Token Index: 79

Text #18

Max Range: 3.6522. Min Range: -3.6522

Max Act: 3.1915. Min Act: -0.0002

Data Index: 157454 (C4 (Web Text))

Max Activating Token Index: 23

Text #19

Max Range: 3.6522. Min Range: -3.6522

Max Act: 3.1582. Min Act: -0.0002

Data Index: 429643 (C4 (Web Text))

Max Activating Token Index: 93