Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 903 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4326. Min Range: -0.4326

Max Act: 0.4326. Min Act: -0.0001

Data Index: 1150014 (C4 (Web Text))

Max Activating Token Index: 310

Text #1

Max Range: 0.4326. Min Range: -0.4326

Max Act: 0.3927. Min Act: -0.0001

Data Index: 989646 (C4 (Web Text))

Max Activating Token Index: 631

Text #2

Max Range: 0.4326. Min Range: -0.4326

Max Act: 0.4197. Min Act: -0.0001

Data Index: 219456 (C4 (Web Text))

Max Activating Token Index: 374

Text #3

Max Range: 0.4326. Min Range: -0.4326

Max Act: 0.3837. Min Act: -0.0001

Data Index: 1117726 (C4 (Web Text))

Max Activating Token Index: 466

Text #4

Max Range: 0.4326. Min Range: -0.4326

Max Act: 0.3738. Min Act: -0.0001

Data Index: 1200923 (C4 (Web Text))

Max Activating Token Index: 594

Text #5

Max Range: 0.4326. Min Range: -0.4326

Max Act: 0.3568. Min Act: -0.0001

Data Index: 1001350 (C4 (Web Text))

Max Activating Token Index: 567

Text #6

Max Range: 0.4326. Min Range: -0.4326

Max Act: 0.3490. Min Act: -0.0001

Data Index: 539302 (C4 (Web Text))

Max Activating Token Index: 29

Text #7

Max Range: 0.4326. Min Range: -0.4326

Max Act: 0.3583. Min Act: -0.0001

Data Index: 1274660 (C4 (Web Text))

Max Activating Token Index: 230

Text #8

Max Range: 0.4326. Min Range: -0.4326

Max Act: 0.3431. Min Act: -0.0001

Data Index: 463934 (C4 (Web Text))

Max Activating Token Index: 251

Text #9

Max Range: 0.4326. Min Range: -0.4326

Max Act: 0.3344. Min Act: -0.0001

Data Index: 282515 (C4 (Web Text))

Max Activating Token Index: 703

Text #10

Max Range: 0.4326. Min Range: -0.4326

Max Act: 0.3228. Min Act: -0.0001

Data Index: 674193 (C4 (Web Text))

Max Activating Token Index: 551

Text #11

Max Range: 0.4326. Min Range: -0.4326

Max Act: 0.3423. Min Act: -0.0001

Data Index: 666681 (C4 (Web Text))

Max Activating Token Index: 108

Text #12

Max Range: 0.4326. Min Range: -0.4326

Max Act: 0.3299. Min Act: -0.0001

Data Index: 314010 (C4 (Web Text))

Max Activating Token Index: 808

Text #13

Max Range: 0.4326. Min Range: -0.4326

Max Act: 0.3074. Min Act: -0.0001

Data Index: 387900 (C4 (Web Text))

Max Activating Token Index: 759

Text #14

Max Range: 0.4326. Min Range: -0.4326

Max Act: 0.3175. Min Act: -0.0001

Data Index: 1062603 (C4 (Web Text))

Max Activating Token Index: 840

Text #15

Max Range: 0.4326. Min Range: -0.4326

Max Act: 0.3189. Min Act: -0.0001

Data Index: 390951 (C4 (Web Text))

Max Activating Token Index: 644

Text #16

Max Range: 0.4326. Min Range: -0.4326

Max Act: 0.3171. Min Act: -0.0001

Data Index: 1284007 (C4 (Web Text))

Max Activating Token Index: 583

Text #17

Max Range: 0.4326. Min Range: -0.4326

Max Act: 0.3147. Min Act: -0.0001

Data Index: 129040 (C4 (Web Text))

Max Activating Token Index: 1008

Text #18

Max Range: 0.4326. Min Range: -0.4326

Max Act: 0.3237. Min Act: -0.0001

Data Index: 118632 (C4 (Web Text))

Max Activating Token Index: 378

Text #19

Max Range: 0.4326. Min Range: -0.4326

Max Act: 0.3227. Min Act: -0.0001

Data Index: 832569 (C4 (Web Text))

Max Activating Token Index: 536