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

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

Neuron 5145 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9901. Min Range: -5.9901

Max Act: 5.9901. Min Act: -0.0001

Data Index: 924886 (C4 (Web Text))

Max Activating Token Index: 910

Text #1

Max Range: 5.9901. Min Range: -5.9901

Max Act: 5.6068. Min Act: -0.0001

Data Index: 953003 (C4 (Web Text))

Max Activating Token Index: 163

Text #2

Max Range: 5.9901. Min Range: -5.9901

Max Act: 5.5421. Min Act: -0.0001

Data Index: 570619 (C4 (Web Text))

Max Activating Token Index: 925

Text #3

Max Range: 5.9901. Min Range: -5.9901

Max Act: 5.1171. Min Act: -0.0001

Data Index: 466850 (C4 (Web Text))

Max Activating Token Index: 54

Text #4

Max Range: 5.9901. Min Range: -5.9901

Max Act: 5.0624. Min Act: -0.0001

Data Index: 634792 (C4 (Web Text))

Max Activating Token Index: 422

Text #5

Max Range: 5.9901. Min Range: -5.9901

Max Act: 4.5511. Min Act: -0.0001

Data Index: 982968 (C4 (Web Text))

Max Activating Token Index: 540

Text #6

Max Range: 5.9901. Min Range: -5.9901

Max Act: 4.8964. Min Act: -0.0001

Data Index: 1191001 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 5.9901. Min Range: -5.9901

Max Act: 4.5665. Min Act: -0.0001

Data Index: 1238288 (C4 (Web Text))

Max Activating Token Index: 372

Text #8

Max Range: 5.9901. Min Range: -5.9901

Max Act: 4.4613. Min Act: -0.0001

Data Index: 54387 (C4 (Web Text))

Max Activating Token Index: 130

Text #9

Max Range: 5.9901. Min Range: -5.9901

Max Act: 4.5732. Min Act: -0.0001

Data Index: 252436 (C4 (Web Text))

Max Activating Token Index: 301

Text #10

Max Range: 5.9901. Min Range: -5.9901

Max Act: 4.2299. Min Act: -0.0001

Data Index: 959322 (C4 (Web Text))

Max Activating Token Index: 765

Text #11

Max Range: 5.9901. Min Range: -5.9901

Max Act: 4.3131. Min Act: -0.0001

Data Index: 93363 (C4 (Web Text))

Max Activating Token Index: 108

Text #12

Max Range: 5.9901. Min Range: -5.9901

Max Act: 4.1557. Min Act: -0.0001

Data Index: 1185203 (C4 (Web Text))

Max Activating Token Index: 707

Text #13

Max Range: 5.9901. Min Range: -5.9901

Max Act: 3.9884. Min Act: -0.0001

Data Index: 389559 (C4 (Web Text))

Max Activating Token Index: 834

Text #14

Max Range: 5.9901. Min Range: -5.9901

Max Act: 4.2561. Min Act: -0.0001

Data Index: 562405 (C4 (Web Text))

Max Activating Token Index: 201

Text #15

Max Range: 5.9901. Min Range: -5.9901

Max Act: 4.2382. Min Act: -0.0001

Data Index: 424628 (C4 (Web Text))

Max Activating Token Index: 103

Text #16

Max Range: 5.9901. Min Range: -5.9901

Max Act: 4.0963. Min Act: -0.0001

Data Index: 113230 (C4 (Web Text))

Max Activating Token Index: 810

Text #17

Max Range: 5.9901. Min Range: -5.9901

Max Act: 4.2445. Min Act: -0.0001

Data Index: 822064 (C4 (Web Text))

Max Activating Token Index: 78

Text #18

Max Range: 5.9901. Min Range: -5.9901

Max Act: 4.0347. Min Act: -0.0001

Data Index: 349236 (C4 (Web Text))

Max Activating Token Index: 1016

Text #19

Max Range: 5.9901. Min Range: -5.9901

Max Act: 3.6959. Min Act: -0.0001

Data Index: 1130887 (C4 (Web Text))

Max Activating Token Index: 895