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

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

Neuron 789 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.3149. Min Act: -0.0001

Data Index: 309582 (C4 (Web Text))

Max Activating Token Index: 960

Text #1

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.3165. Min Act: -0.0001

Data Index: 907066 (C4 (Web Text))

Max Activating Token Index: 436

Text #2

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.3358. Min Act: -0.0001

Data Index: 1047518 (C4 (Web Text))

Max Activating Token Index: 67

Text #3

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.3184. Min Act: -0.0001

Data Index: 238378 (C4 (Web Text))

Max Activating Token Index: 958

Text #4

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2945. Min Act: -0.0001

Data Index: 280227 (C4 (Web Text))

Max Activating Token Index: 257

Text #5

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2882. Min Act: -0.0001

Data Index: 844668 (C4 (Web Text))

Max Activating Token Index: 979

Text #6

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.3136. Min Act: -0.0001

Data Index: 60500 (C4 (Web Text))

Max Activating Token Index: 209

Text #7

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2827. Min Act: -0.0001

Data Index: 53967 (C4 (Web Text))

Max Activating Token Index: 412

Text #8

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2867. Min Act: -0.0001

Data Index: 517297 (C4 (Web Text))

Max Activating Token Index: 601

Text #9

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2884. Min Act: -0.0001

Data Index: 677213 (C4 (Web Text))

Max Activating Token Index: 748

Text #10

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.3294. Min Act: -0.0001

Data Index: 192631 (C4 (Web Text))

Max Activating Token Index: 625

Text #11

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2845. Min Act: -0.0001

Data Index: 724304 (C4 (Web Text))

Max Activating Token Index: 324

Text #12

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.3216. Min Act: -0.0001

Data Index: 389588 (C4 (Web Text))

Max Activating Token Index: 1013

Text #13

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2471. Min Act: -0.0001

Data Index: 700433 (C4 (Web Text))

Max Activating Token Index: 947

Text #14

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2784. Min Act: -0.0001

Data Index: 44863 (C4 (Web Text))

Max Activating Token Index: 145

Text #15

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2648. Min Act: -0.0001

Data Index: 123061 (C4 (Web Text))

Max Activating Token Index: 244

Text #16

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2814. Min Act: -0.0001

Data Index: 1172627 (C4 (Web Text))

Max Activating Token Index: 686

Text #17

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2523. Min Act: -0.0001

Data Index: 1019126 (C4 (Web Text))

Max Activating Token Index: 466

Text #18

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2632. Min Act: -0.0001

Data Index: 769690 (C4 (Web Text))

Max Activating Token Index: 222

Text #19

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2609. Min Act: -0.0001

Data Index: 1082672 (C4 (Web Text))

Max Activating Token Index: 782