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

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

Neuron 2606 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: 1.8749. Min Range: -1.8749

Max Act: 1.8749. Min Act: -0.0002

Data Index: 957900 (C4 (Web Text))

Max Activating Token Index: 212

Text #1

Max Range: 1.8749. Min Range: -1.8749

Max Act: 1.8264. Min Act: -0.0002

Data Index: 1019773 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 1.8749. Min Range: -1.8749

Max Act: 1.7553. Min Act: -0.0002

Data Index: 1204784 (C4 (Web Text))

Max Activating Token Index: 626

Text #3

Max Range: 1.8749. Min Range: -1.8749

Max Act: 1.7047. Min Act: -0.0002

Data Index: 1261092 (C4 (Web Text))

Max Activating Token Index: 326

Text #4

Max Range: 1.8749. Min Range: -1.8749

Max Act: 1.6601. Min Act: -0.0002

Data Index: 592436 (C4 (Web Text))

Max Activating Token Index: 17

Text #5

Max Range: 1.8749. Min Range: -1.8749

Max Act: 1.6367. Min Act: -0.0002

Data Index: 685248 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 1.8749. Min Range: -1.8749

Max Act: 1.6912. Min Act: -0.0002

Data Index: 1334482 (C4 (Web Text))

Max Activating Token Index: 428

Text #7

Max Range: 1.8749. Min Range: -1.8749

Max Act: 1.6545. Min Act: -0.0002

Data Index: 553795 (C4 (Web Text))

Max Activating Token Index: 764

Text #8

Max Range: 1.8749. Min Range: -1.8749

Max Act: 1.6670. Min Act: -0.0002

Data Index: 263909 (C4 (Web Text))

Max Activating Token Index: 75

Text #9

Max Range: 1.8749. Min Range: -1.8749

Max Act: 1.6663. Min Act: -0.0002

Data Index: 770293 (C4 (Web Text))

Max Activating Token Index: 73

Text #10

Max Range: 1.8749. Min Range: -1.8749

Max Act: 1.6397. Min Act: -0.0002

Data Index: 364185 (C4 (Web Text))

Max Activating Token Index: 736

Text #11

Max Range: 1.8749. Min Range: -1.8749

Max Act: 1.6227. Min Act: -0.0002

Data Index: 833486 (C4 (Web Text))

Max Activating Token Index: 31

Text #12

Max Range: 1.8749. Min Range: -1.8749

Max Act: 1.6740. Min Act: -0.0002

Data Index: 1058293 (C4 (Web Text))

Max Activating Token Index: 50

Text #13

Max Range: 1.8749. Min Range: -1.8749

Max Act: 1.5789. Min Act: -0.0002

Data Index: 874164 (C4 (Web Text))

Max Activating Token Index: 208

Text #14

Max Range: 1.8749. Min Range: -1.8749

Max Act: 1.6296. Min Act: -0.0002

Data Index: 812132 (C4 (Web Text))

Max Activating Token Index: 240

Text #15

Max Range: 1.8749. Min Range: -1.8749

Max Act: 1.5849. Min Act: -0.0002

Data Index: 277302 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 1.8749. Min Range: -1.8749

Max Act: 1.6231. Min Act: -0.0002

Data Index: 589872 (C4 (Web Text))

Max Activating Token Index: 68

Text #17

Max Range: 1.8749. Min Range: -1.8749

Max Act: 1.5933. Min Act: -0.0002

Data Index: 220233 (C4 (Web Text))

Max Activating Token Index: 715

Text #18

Max Range: 1.8749. Min Range: -1.8749

Max Act: 1.5813. Min Act: -0.0002

Data Index: 679674 (C4 (Web Text))

Max Activating Token Index: 560

Text #19

Max Range: 1.8749. Min Range: -1.8749

Max Act: 1.5570. Min Act: -0.0002

Data Index: 1317689 (C4 (Web Text))

Max Activating Token Index: 637