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

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

Neuron 1131 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: 2.5407. Min Range: -2.5407

Max Act: 2.5407. Min Act: -0.0002

Data Index: 1173186 (C4 (Web Text))

Max Activating Token Index: 454

Text #1

Max Range: 2.5407. Min Range: -2.5407

Max Act: 2.3831. Min Act: -0.0002

Data Index: 786926 (C4 (Web Text))

Max Activating Token Index: 498

Text #2

Max Range: 2.5407. Min Range: -2.5407

Max Act: 2.3704. Min Act: -0.0002

Data Index: 420208 (C4 (Web Text))

Max Activating Token Index: 580

Text #3

Max Range: 2.5407. Min Range: -2.5407

Max Act: 2.2971. Min Act: -0.0002

Data Index: 297346 (C4 (Web Text))

Max Activating Token Index: 276

Text #4

Max Range: 2.5407. Min Range: -2.5407

Max Act: 2.2635. Min Act: -0.0002

Data Index: 1200340 (C4 (Web Text))

Max Activating Token Index: 743

Text #5

Max Range: 2.5407. Min Range: -2.5407

Max Act: 2.2302. Min Act: -0.0002

Data Index: 814657 (C4 (Web Text))

Max Activating Token Index: 624

Text #6

Max Range: 2.5407. Min Range: -2.5407

Max Act: 2.2260. Min Act: -0.0002

Data Index: 434368 (C4 (Web Text))

Max Activating Token Index: 13

Text #7

Max Range: 2.5407. Min Range: -2.5407

Max Act: 2.2161. Min Act: -0.0002

Data Index: 781297 (C4 (Web Text))

Max Activating Token Index: 331

Text #8

Max Range: 2.5407. Min Range: -2.5407

Max Act: 2.2097. Min Act: -0.0002

Data Index: 166198 (C4 (Web Text))

Max Activating Token Index: 63

Text #9

Max Range: 2.5407. Min Range: -2.5407

Max Act: 2.2163. Min Act: -0.0002

Data Index: 845670 (C4 (Web Text))

Max Activating Token Index: 8

Text #10

Max Range: 2.5407. Min Range: -2.5407

Max Act: 2.1631. Min Act: -0.0002

Data Index: 601434 (C4 (Web Text))

Max Activating Token Index: 2

Text #11

Max Range: 2.5407. Min Range: -2.5407

Max Act: 2.1631. Min Act: -0.0002

Data Index: 1047763 (C4 (Web Text))

Max Activating Token Index: 2

Text #12

Max Range: 2.5407. Min Range: -2.5407

Max Act: 2.2255. Min Act: -0.0002

Data Index: 1301105 (C4 (Web Text))

Max Activating Token Index: 318

Text #13

Max Range: 2.5407. Min Range: -2.5407

Max Act: 2.2186. Min Act: -0.0002

Data Index: 451674 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 2.5407. Min Range: -2.5407

Max Act: 2.1509. Min Act: -0.0002

Data Index: 901546 (C4 (Web Text))

Max Activating Token Index: 9

Text #15

Max Range: 2.5407. Min Range: -2.5407

Max Act: 2.1331. Min Act: -0.0002

Data Index: 942218 (C4 (Web Text))

Max Activating Token Index: 417

Text #16

Max Range: 2.5407. Min Range: -2.5407

Max Act: 2.1017. Min Act: -0.0002

Data Index: 684218 (C4 (Web Text))

Max Activating Token Index: 274

Text #17

Max Range: 2.5407. Min Range: -2.5407

Max Act: 2.1824. Min Act: -0.0002

Data Index: 299420 (C4 (Web Text))

Max Activating Token Index: 556

Text #18

Max Range: 2.5407. Min Range: -2.5407

Max Act: 2.1230. Min Act: -0.0002

Data Index: 895357 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 2.5407. Min Range: -2.5407

Max Act: 2.1742. Min Act: -0.0002

Data Index: 515320 (C4 (Web Text))

Max Activating Token Index: 443