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

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

Neuron 4618 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: 1.1781. Min Range: -1.1781

Max Act: 1.1781. Min Act: -0.0002

Data Index: 681071 (C4 (Web Text))

Max Activating Token Index: 806

Text #1

Max Range: 1.1781. Min Range: -1.1781

Max Act: 1.1770. Min Act: -0.0002

Data Index: 358136 (C4 (Web Text))

Max Activating Token Index: 715

Text #2

Max Range: 1.1781. Min Range: -1.1781

Max Act: 1.1504. Min Act: -0.0002

Data Index: 658130 (C4 (Web Text))

Max Activating Token Index: 624

Text #3

Max Range: 1.1781. Min Range: -1.1781

Max Act: 1.1591. Min Act: -0.0002

Data Index: 220097 (C4 (Web Text))

Max Activating Token Index: 764

Text #4

Max Range: 1.1781. Min Range: -1.1781

Max Act: 1.1203. Min Act: -0.0002

Data Index: 326968 (C4 (Web Text))

Max Activating Token Index: 854

Text #5

Max Range: 1.1781. Min Range: -1.1781

Max Act: 1.1529. Min Act: -0.0002

Data Index: 672982 (C4 (Web Text))

Max Activating Token Index: 546

Text #6

Max Range: 1.1781. Min Range: -1.1781

Max Act: 1.1419. Min Act: -0.0002

Data Index: 1356759 (C4 (Web Text))

Max Activating Token Index: 841

Text #7

Max Range: 1.1781. Min Range: -1.1781

Max Act: 1.1171. Min Act: -0.0002

Data Index: 578685 (C4 (Web Text))

Max Activating Token Index: 471

Text #8

Max Range: 1.1781. Min Range: -1.1781

Max Act: 1.0963. Min Act: -0.0002

Data Index: 90213 (C4 (Web Text))

Max Activating Token Index: 967

Text #9

Max Range: 1.1781. Min Range: -1.1781

Max Act: 1.1189. Min Act: -0.0002

Data Index: 549606 (C4 (Web Text))

Max Activating Token Index: 187

Text #10

Max Range: 1.1781. Min Range: -1.1781

Max Act: 1.1067. Min Act: -0.0002

Data Index: 275139 (C4 (Web Text))

Max Activating Token Index: 816

Text #11

Max Range: 1.1781. Min Range: -1.1781

Max Act: 1.0756. Min Act: -0.0002

Data Index: 126205 (C4 (Web Text))

Max Activating Token Index: 805

Text #12

Max Range: 1.1781. Min Range: -1.1781

Max Act: 1.0974. Min Act: -0.0002

Data Index: 241561 (C4 (Web Text))

Max Activating Token Index: 143

Text #13

Max Range: 1.1781. Min Range: -1.1781

Max Act: 1.0994. Min Act: -0.0002

Data Index: 449543 (C4 (Web Text))

Max Activating Token Index: 930

Text #14

Max Range: 1.1781. Min Range: -1.1781

Max Act: 1.0930. Min Act: -0.0002

Data Index: 741219 (C4 (Web Text))

Max Activating Token Index: 491

Text #15

Max Range: 1.1781. Min Range: -1.1781

Max Act: 1.0876. Min Act: -0.0002

Data Index: 876074 (C4 (Web Text))

Max Activating Token Index: 670

Text #16

Max Range: 1.1781. Min Range: -1.1781

Max Act: 1.0737. Min Act: -0.0002

Data Index: 1060056 (C4 (Web Text))

Max Activating Token Index: 320

Text #17

Max Range: 1.1781. Min Range: -1.1781

Max Act: 1.0579. Min Act: -0.0002

Data Index: 209487 (C4 (Web Text))

Max Activating Token Index: 604

Text #18

Max Range: 1.1781. Min Range: -1.1781

Max Act: 1.0587. Min Act: -0.0002

Data Index: 1097108 (C4 (Web Text))

Max Activating Token Index: 456

Text #19

Max Range: 1.1781. Min Range: -1.1781

Max Act: 1.0337. Min Act: -0.0002

Data Index: 1280546 (C4 (Web Text))

Max Activating Token Index: 298