Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3497 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3366. Min Range: -0.3366

Max Act: 0.3207. Min Act: -0.0001

Data Index: 449532 (C4 (Web Text))

Max Activating Token Index: 726

Text #1

Max Range: 0.3366. Min Range: -0.3366

Max Act: 0.3298. Min Act: -0.0001

Data Index: 432127 (C4 (Web Text))

Max Activating Token Index: 486

Text #2

Max Range: 0.3366. Min Range: -0.3366

Max Act: 0.3366. Min Act: -0.0000

Data Index: 637632 (C4 (Web Text))

Max Activating Token Index: 968

Text #3

Max Range: 0.3366. Min Range: -0.3366

Max Act: 0.3268. Min Act: -0.0001

Data Index: 1176915 (C4 (Web Text))

Max Activating Token Index: 489

Text #4

Max Range: 0.3366. Min Range: -0.3366

Max Act: 0.3109. Min Act: -0.0000

Data Index: 316407 (C4 (Web Text))

Max Activating Token Index: 88

Text #5

Max Range: 0.3366. Min Range: -0.3366

Max Act: 0.2763. Min Act: -0.0001

Data Index: 180015 (C4 (Web Text))

Max Activating Token Index: 690

Text #6

Max Range: 0.3366. Min Range: -0.3366

Max Act: 0.2712. Min Act: -0.0001

Data Index: 258792 (C4 (Web Text))

Max Activating Token Index: 113

Text #7

Max Range: 0.3366. Min Range: -0.3366

Max Act: 0.2604. Min Act: -0.0001

Data Index: 1205293 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 0.3366. Min Range: -0.3366

Max Act: 0.2727. Min Act: -0.0000

Data Index: 935512 (C4 (Web Text))

Max Activating Token Index: 799

Text #9

Max Range: 0.3366. Min Range: -0.3366

Max Act: 0.2739. Min Act: -0.0001

Data Index: 968017 (C4 (Web Text))

Max Activating Token Index: 556

Text #10

Max Range: 0.3366. Min Range: -0.3366

Max Act: 0.2786. Min Act: -0.0001

Data Index: 1130500 (C4 (Web Text))

Max Activating Token Index: 934

Text #11

Max Range: 0.3366. Min Range: -0.3366

Max Act: 0.2667. Min Act: -0.0001

Data Index: 362010 (C4 (Web Text))

Max Activating Token Index: 640

Text #12

Max Range: 0.3366. Min Range: -0.3366

Max Act: 0.2504. Min Act: -0.0001

Data Index: 244900 (C4 (Web Text))

Max Activating Token Index: 770

Text #13

Max Range: 0.3366. Min Range: -0.3366

Max Act: 0.2506. Min Act: -0.0001

Data Index: 84568 (C4 (Web Text))

Max Activating Token Index: 971

Text #14

Max Range: 0.3366. Min Range: -0.3366

Max Act: 0.2518. Min Act: -0.0001

Data Index: 242498 (C4 (Web Text))

Max Activating Token Index: 824

Text #15

Max Range: 0.3366. Min Range: -0.3366

Max Act: 0.2503. Min Act: -0.0001

Data Index: 184676 (C4 (Web Text))

Max Activating Token Index: 470

Text #16

Max Range: 0.3366. Min Range: -0.3366

Max Act: 0.2575. Min Act: -0.0000

Data Index: 399307 (C4 (Web Text))

Max Activating Token Index: 773

Text #17

Max Range: 0.3366. Min Range: -0.3366

Max Act: 0.2448. Min Act: -0.0001

Data Index: 1261241 (C4 (Web Text))

Max Activating Token Index: 703

Text #18

Max Range: 0.3366. Min Range: -0.3366

Max Act: 0.2455. Min Act: -0.0001

Data Index: 579183 (C4 (Web Text))

Max Activating Token Index: 322

Text #19

Max Range: 0.3366. Min Range: -0.3366

Max Act: 0.2419. Min Act: -0.0000

Data Index: 388118 (C4 (Web Text))

Max Activating Token Index: 79