Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 51 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.3527. Min Range: -0.3527

Max Act: 0.3176. Min Act: -0.0005

Data Index: 957777 (C4 (Web Text))

Max Activating Token Index: 786

Text #1

Max Range: 0.3527. Min Range: -0.3527

Max Act: 0.3527. Min Act: -0.0005

Data Index: 1308689 (C4 (Web Text))

Max Activating Token Index: 466

Text #2

Max Range: 0.3527. Min Range: -0.3527

Max Act: 0.3410. Min Act: -0.0005

Data Index: 25720 (C4 (Web Text))

Max Activating Token Index: 568

Text #3

Max Range: 0.3527. Min Range: -0.3527

Max Act: 0.3356. Min Act: -0.0005

Data Index: 829175 (C4 (Web Text))

Max Activating Token Index: 927

Text #4

Max Range: 0.3527. Min Range: -0.3527

Max Act: 0.3335. Min Act: -0.0005

Data Index: 1037178 (C4 (Web Text))

Max Activating Token Index: 757

Text #5

Max Range: 0.3527. Min Range: -0.3527

Max Act: 0.3409. Min Act: -0.0005

Data Index: 818139 (C4 (Web Text))

Max Activating Token Index: 786

Text #6

Max Range: 0.3527. Min Range: -0.3527

Max Act: 0.3287. Min Act: -0.0005

Data Index: 912637 (C4 (Web Text))

Max Activating Token Index: 572

Text #7

Max Range: 0.3527. Min Range: -0.3527

Max Act: 0.3388. Min Act: -0.0005

Data Index: 286498 (C4 (Web Text))

Max Activating Token Index: 519

Text #8

Max Range: 0.3527. Min Range: -0.3527

Max Act: 0.3117. Min Act: -0.0005

Data Index: 1234160 (C4 (Web Text))

Max Activating Token Index: 472

Text #9

Max Range: 0.3527. Min Range: -0.3527

Max Act: 0.2983. Min Act: -0.0005

Data Index: 325819 (C4 (Web Text))

Max Activating Token Index: 868

Text #10

Max Range: 0.3527. Min Range: -0.3527

Max Act: 0.3200. Min Act: -0.0005

Data Index: 1330614 (C4 (Web Text))

Max Activating Token Index: 689

Text #11

Max Range: 0.3527. Min Range: -0.3527

Max Act: 0.3187. Min Act: -0.0005

Data Index: 323725 (C4 (Web Text))

Max Activating Token Index: 70

Text #12

Max Range: 0.3527. Min Range: -0.3527

Max Act: 0.2858. Min Act: -0.0005

Data Index: 729719 (C4 (Web Text))

Max Activating Token Index: 646

Text #13

Max Range: 0.3527. Min Range: -0.3527

Max Act: 0.2979. Min Act: -0.0005

Data Index: 1186314 (C4 (Web Text))

Max Activating Token Index: 310

Text #14

Max Range: 0.3527. Min Range: -0.3527

Max Act: 0.3253. Min Act: -0.0005

Data Index: 229062 (C4 (Web Text))

Max Activating Token Index: 752

Text #15

Max Range: 0.3527. Min Range: -0.3527

Max Act: 0.3361. Min Act: -0.0005

Data Index: 157301 (C4 (Web Text))

Max Activating Token Index: 771

Text #16

Max Range: 0.3527. Min Range: -0.3527

Max Act: 0.2473. Min Act: -0.0005

Data Index: 1032773 (C4 (Web Text))

Max Activating Token Index: 672

Text #17

Max Range: 0.3527. Min Range: -0.3527

Max Act: 0.2903. Min Act: -0.0005

Data Index: 1179384 (C4 (Web Text))

Max Activating Token Index: 874

Text #18

Max Range: 0.3527. Min Range: -0.3527

Max Act: 0.3226. Min Act: -0.0005

Data Index: 790582 (C4 (Web Text))

Max Activating Token Index: 529

Text #19

Max Range: 0.3527. Min Range: -0.3527

Max Act: 0.2873. Min Act: -0.0005

Data Index: 71080 (C4 (Web Text))

Max Activating Token Index: 460