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

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

Neuron 5552 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.6461. Min Range: -2.6461

Max Act: 2.5213. Min Act: -0.0000

Data Index: 127615 (C4 (Web Text))

Max Activating Token Index: 867

Text #1

Max Range: 2.6461. Min Range: -2.6461

Max Act: 2.4250. Min Act: -0.0000

Data Index: 509475 (C4 (Web Text))

Max Activating Token Index: 639

Text #2

Max Range: 2.6461. Min Range: -2.6461

Max Act: 2.6461. Min Act: -0.0000

Data Index: 517096 (C4 (Web Text))

Max Activating Token Index: 467

Text #3

Max Range: 2.6461. Min Range: -2.6461

Max Act: 2.2781. Min Act: -0.0000

Data Index: 146542 (C4 (Web Text))

Max Activating Token Index: 405

Text #4

Max Range: 2.6461. Min Range: -2.6461

Max Act: 2.3856. Min Act: -0.0000

Data Index: 738217 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 2.6461. Min Range: -2.6461

Max Act: 2.1233. Min Act: -0.0000

Data Index: 117646 (C4 (Web Text))

Max Activating Token Index: 901

Text #6

Max Range: 2.6461. Min Range: -2.6461

Max Act: 2.3993. Min Act: -0.0000

Data Index: 432568 (C4 (Web Text))

Max Activating Token Index: 282

Text #7

Max Range: 2.6461. Min Range: -2.6461

Max Act: 2.2810. Min Act: -0.0000

Data Index: 962588 (C4 (Web Text))

Max Activating Token Index: 675

Text #8

Max Range: 2.6461. Min Range: -2.6461

Max Act: 2.4001. Min Act: -0.0000

Data Index: 464415 (C4 (Web Text))

Max Activating Token Index: 264

Text #9

Max Range: 2.6461. Min Range: -2.6461

Max Act: 2.1921. Min Act: -0.0000

Data Index: 673062 (C4 (Web Text))

Max Activating Token Index: 769

Text #10

Max Range: 2.6461. Min Range: -2.6461

Max Act: 2.2032. Min Act: -0.0000

Data Index: 747810 (C4 (Web Text))

Max Activating Token Index: 258

Text #11

Max Range: 2.6461. Min Range: -2.6461

Max Act: 2.1957. Min Act: -0.0000

Data Index: 721991 (C4 (Web Text))

Max Activating Token Index: 89

Text #12

Max Range: 2.6461. Min Range: -2.6461

Max Act: 2.0750. Min Act: -0.0000

Data Index: 914471 (C4 (Web Text))

Max Activating Token Index: 302

Text #13

Max Range: 2.6461. Min Range: -2.6461

Max Act: 2.1776. Min Act: -0.0000

Data Index: 90600 (C4 (Web Text))

Max Activating Token Index: 107

Text #14

Max Range: 2.6461. Min Range: -2.6461

Max Act: 2.2641. Min Act: -0.0000

Data Index: 802760 (C4 (Web Text))

Max Activating Token Index: 856

Text #15

Max Range: 2.6461. Min Range: -2.6461

Max Act: 2.2486. Min Act: -0.0000

Data Index: 895376 (C4 (Web Text))

Max Activating Token Index: 756

Text #16

Max Range: 2.6461. Min Range: -2.6461

Max Act: 2.0224. Min Act: -0.0000

Data Index: 472727 (C4 (Web Text))

Max Activating Token Index: 929

Text #17

Max Range: 2.6461. Min Range: -2.6461

Max Act: 2.1044. Min Act: -0.0000

Data Index: 787392 (C4 (Web Text))

Max Activating Token Index: 380

Text #18

Max Range: 2.6461. Min Range: -2.6461

Max Act: 2.1008. Min Act: -0.0000

Data Index: 105509 (C4 (Web Text))

Max Activating Token Index: 415

Text #19

Max Range: 2.6461. Min Range: -2.6461

Max Act: 2.0845. Min Act: -0.0000

Data Index: 871758 (C4 (Web Text))

Max Activating Token Index: 953