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

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

Neuron 2313 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: 1.4701. Min Range: -1.4701

Max Act: 1.4701. Min Act: -0.0002

Data Index: 1185543 (C4 (Web Text))

Max Activating Token Index: 622

Text #1

Max Range: 1.4701. Min Range: -1.4701

Max Act: 1.3909. Min Act: -0.0002

Data Index: 913452 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 1.4701. Min Range: -1.4701

Max Act: 1.3586. Min Act: -0.0003

Data Index: 1217643 (C4 (Web Text))

Max Activating Token Index: 366

Text #3

Max Range: 1.4701. Min Range: -1.4701

Max Act: 1.3639. Min Act: -0.0002

Data Index: 1188735 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 1.4701. Min Range: -1.4701

Max Act: 1.3413. Min Act: -0.0002

Data Index: 419956 (C4 (Web Text))

Max Activating Token Index: 127

Text #5

Max Range: 1.4701. Min Range: -1.4701

Max Act: 1.3374. Min Act: -0.0002

Data Index: 1148427 (C4 (Web Text))

Max Activating Token Index: 52

Text #6

Max Range: 1.4701. Min Range: -1.4701

Max Act: 1.3205. Min Act: -0.0002

Data Index: 1188250 (C4 (Web Text))

Max Activating Token Index: 15

Text #7

Max Range: 1.4701. Min Range: -1.4701

Max Act: 1.2998. Min Act: -0.0002

Data Index: 433872 (C4 (Web Text))

Max Activating Token Index: 545

Text #8

Max Range: 1.4701. Min Range: -1.4701

Max Act: 1.2897. Min Act: -0.0002

Data Index: 699773 (C4 (Web Text))

Max Activating Token Index: 227

Text #9

Max Range: 1.4701. Min Range: -1.4701

Max Act: 1.2957. Min Act: -0.0002

Data Index: 629795 (C4 (Web Text))

Max Activating Token Index: 588

Text #10

Max Range: 1.4701. Min Range: -1.4701

Max Act: 1.2477. Min Act: -0.0002

Data Index: 651044 (C4 (Web Text))

Max Activating Token Index: 348

Text #11

Max Range: 1.4701. Min Range: -1.4701

Max Act: 1.2576. Min Act: -0.0002

Data Index: 586496 (C4 (Web Text))

Max Activating Token Index: 363

Text #12

Max Range: 1.4701. Min Range: -1.4701

Max Act: 1.2581. Min Act: -0.0002

Data Index: 705389 (C4 (Web Text))

Max Activating Token Index: 582

Text #13

Max Range: 1.4701. Min Range: -1.4701

Max Act: 1.2148. Min Act: -0.0003

Data Index: 1298669 (C4 (Web Text))

Max Activating Token Index: 62

Text #14

Max Range: 1.4701. Min Range: -1.4701

Max Act: 1.2387. Min Act: -0.0002

Data Index: 592816 (C4 (Web Text))

Max Activating Token Index: 215

Text #15

Max Range: 1.4701. Min Range: -1.4701

Max Act: 1.2310. Min Act: -0.0002

Data Index: 1078625 (C4 (Web Text))

Max Activating Token Index: 596

Text #16

Max Range: 1.4701. Min Range: -1.4701

Max Act: 1.2140. Min Act: -0.0003

Data Index: 248202 (C4 (Web Text))

Max Activating Token Index: 757

Text #17

Max Range: 1.4701. Min Range: -1.4701

Max Act: 1.2150. Min Act: -0.0003

Data Index: 1292046 (C4 (Web Text))

Max Activating Token Index: 95

Text #18

Max Range: 1.4701. Min Range: -1.4701

Max Act: 1.1973. Min Act: -0.0002

Data Index: 1132176 (C4 (Web Text))

Max Activating Token Index: 449

Text #19

Max Range: 1.4701. Min Range: -1.4701

Max Act: 1.2246. Min Act: -0.0002

Data Index: 747136 (C4 (Web Text))

Max Activating Token Index: 174