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

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

Neuron 1439 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: 1.1653. Min Range: -1.1653

Max Act: 1.1653. Min Act: -0.0002

Data Index: 954945 (C4 (Web Text))

Max Activating Token Index: 484

Text #1

Max Range: 1.1653. Min Range: -1.1653

Max Act: 1.1118. Min Act: -0.0002

Data Index: 449690 (C4 (Web Text))

Max Activating Token Index: 443

Text #2

Max Range: 1.1653. Min Range: -1.1653

Max Act: 1.0872. Min Act: -0.0002

Data Index: 781679 (C4 (Web Text))

Max Activating Token Index: 375

Text #3

Max Range: 1.1653. Min Range: -1.1653

Max Act: 1.0469. Min Act: -0.0002

Data Index: 1219985 (C4 (Web Text))

Max Activating Token Index: 359

Text #4

Max Range: 1.1653. Min Range: -1.1653

Max Act: 1.0075. Min Act: -0.0002

Data Index: 1120637 (C4 (Web Text))

Max Activating Token Index: 541

Text #5

Max Range: 1.1653. Min Range: -1.1653

Max Act: 1.0281. Min Act: -0.0002

Data Index: 1011413 (C4 (Web Text))

Max Activating Token Index: 921

Text #6

Max Range: 1.1653. Min Range: -1.1653

Max Act: 1.0040. Min Act: -0.0002

Data Index: 1213122 (C4 (Web Text))

Max Activating Token Index: 365

Text #7

Max Range: 1.1653. Min Range: -1.1653

Max Act: 0.9964. Min Act: -0.0002

Data Index: 572660 (C4 (Web Text))

Max Activating Token Index: 764

Text #8

Max Range: 1.1653. Min Range: -1.1653

Max Act: 0.9731. Min Act: -0.0002

Data Index: 1244312 (C4 (Web Text))

Max Activating Token Index: 552

Text #9

Max Range: 1.1653. Min Range: -1.1653

Max Act: 0.9901. Min Act: -0.0002

Data Index: 1307030 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 1.1653. Min Range: -1.1653

Max Act: 0.9559. Min Act: -0.0002

Data Index: 5454 (C4 (Web Text))

Max Activating Token Index: 706

Text #11

Max Range: 1.1653. Min Range: -1.1653

Max Act: 0.9721. Min Act: -0.0002

Data Index: 1110294 (C4 (Web Text))

Max Activating Token Index: 738

Text #12

Max Range: 1.1653. Min Range: -1.1653

Max Act: 0.9681. Min Act: -0.0002

Data Index: 126697 (C4 (Web Text))

Max Activating Token Index: 282

Text #13

Max Range: 1.1653. Min Range: -1.1653

Max Act: 0.9630. Min Act: -0.0002

Data Index: 1344011 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 1.1653. Min Range: -1.1653

Max Act: 0.9548. Min Act: -0.0002

Data Index: 1052158 (C4 (Web Text))

Max Activating Token Index: 333

Text #15

Max Range: 1.1653. Min Range: -1.1653

Max Act: 0.9361. Min Act: -0.0002

Data Index: 868446 (C4 (Web Text))

Max Activating Token Index: 948

Text #16

Max Range: 1.1653. Min Range: -1.1653

Max Act: 0.9386. Min Act: -0.0002

Data Index: 183925 (C4 (Web Text))

Max Activating Token Index: 529

Text #17

Max Range: 1.1653. Min Range: -1.1653

Max Act: 0.9277. Min Act: -0.0002

Data Index: 1027205 (C4 (Web Text))

Max Activating Token Index: 240

Text #18

Max Range: 1.1653. Min Range: -1.1653

Max Act: 0.9282. Min Act: -0.0002

Data Index: 1338039 (C4 (Web Text))

Max Activating Token Index: 54

Text #19

Max Range: 1.1653. Min Range: -1.1653

Max Act: 0.9299. Min Act: -0.0002

Data Index: 898827 (C4 (Web Text))

Max Activating Token Index: 672