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

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

Neuron 968 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7790. Min Range: -0.7790

Max Act: 0.7413. Min Act: -0.0002

Data Index: 463958 (C4 (Web Text))

Max Activating Token Index: 62

Text #1

Max Range: 0.7790. Min Range: -0.7790

Max Act: 0.7746. Min Act: -0.0002

Data Index: 730750 (C4 (Web Text))

Max Activating Token Index: 338

Text #2

Max Range: 0.7790. Min Range: -0.7790

Max Act: 0.7790. Min Act: -0.0001

Data Index: 506006 (C4 (Web Text))

Max Activating Token Index: 196

Text #3

Max Range: 0.7790. Min Range: -0.7790

Max Act: 0.7464. Min Act: -0.0002

Data Index: 847522 (C4 (Web Text))

Max Activating Token Index: 57

Text #4

Max Range: 0.7790. Min Range: -0.7790

Max Act: 0.7626. Min Act: -0.0002

Data Index: 1098858 (C4 (Web Text))

Max Activating Token Index: 307

Text #5

Max Range: 0.7790. Min Range: -0.7790

Max Act: 0.7308. Min Act: -0.0002

Data Index: 927246 (C4 (Web Text))

Max Activating Token Index: 493

Text #6

Max Range: 0.7790. Min Range: -0.7790

Max Act: 0.7025. Min Act: -0.0002

Data Index: 39761 (C4 (Web Text))

Max Activating Token Index: 154

Text #7

Max Range: 0.7790. Min Range: -0.7790

Max Act: 0.7036. Min Act: -0.0002

Data Index: 56510 (C4 (Web Text))

Max Activating Token Index: 147

Text #8

Max Range: 0.7790. Min Range: -0.7790

Max Act: 0.7249. Min Act: -0.0002

Data Index: 510784 (C4 (Web Text))

Max Activating Token Index: 316

Text #9

Max Range: 0.7790. Min Range: -0.7790

Max Act: 0.6975. Min Act: -0.0002

Data Index: 1305540 (C4 (Web Text))

Max Activating Token Index: 307

Text #10

Max Range: 0.7790. Min Range: -0.7790

Max Act: 0.7182. Min Act: -0.0002

Data Index: 563146 (C4 (Web Text))

Max Activating Token Index: 18

Text #11

Max Range: 0.7790. Min Range: -0.7790

Max Act: 0.6803. Min Act: -0.0002

Data Index: 621896 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 0.7790. Min Range: -0.7790

Max Act: 0.6732. Min Act: -0.0002

Data Index: 853208 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 0.7790. Min Range: -0.7790

Max Act: 0.6898. Min Act: -0.0002

Data Index: 1359443 (C4 (Web Text))

Max Activating Token Index: 700

Text #14

Max Range: 0.7790. Min Range: -0.7790

Max Act: 0.6949. Min Act: -0.0001

Data Index: 1335208 (C4 (Web Text))

Max Activating Token Index: 453

Text #15

Max Range: 0.7790. Min Range: -0.7790

Max Act: 0.6891. Min Act: -0.0002

Data Index: 1238515 (C4 (Web Text))

Max Activating Token Index: 84

Text #16

Max Range: 0.7790. Min Range: -0.7790

Max Act: 0.6410. Min Act: -0.0002

Data Index: 1091573 (C4 (Web Text))

Max Activating Token Index: 969

Text #17

Max Range: 0.7790. Min Range: -0.7790

Max Act: 0.7260. Min Act: -0.0002

Data Index: 277252 (C4 (Web Text))

Max Activating Token Index: 491

Text #18

Max Range: 0.7790. Min Range: -0.7790

Max Act: 0.6612. Min Act: -0.0002

Data Index: 461819 (C4 (Web Text))

Max Activating Token Index: 372

Text #19

Max Range: 0.7790. Min Range: -0.7790

Max Act: 0.6412. Min Act: -0.0001

Data Index: 384017 (C4 (Web Text))

Max Activating Token Index: 118