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

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

Neuron 600 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2700. Min Range: -0.2700

Max Act: 0.2700. Min Act: -0.0000

Data Index: 1223628 (C4 (Web Text))

Max Activating Token Index: 495

Text #1

Max Range: 0.2700. Min Range: -0.2700

Max Act: 0.2318. Min Act: -0.0001

Data Index: 1063555 (C4 (Web Text))

Max Activating Token Index: 368

Text #2

Max Range: 0.2700. Min Range: -0.2700

Max Act: 0.2383. Min Act: -0.0001

Data Index: 240376 (C4 (Web Text))

Max Activating Token Index: 166

Text #3

Max Range: 0.2700. Min Range: -0.2700

Max Act: 0.2127. Min Act: -0.0001

Data Index: 481031 (C4 (Web Text))

Max Activating Token Index: 950

Text #4

Max Range: 0.2700. Min Range: -0.2700

Max Act: 0.2270. Min Act: -0.0000

Data Index: 718280 (C4 (Web Text))

Max Activating Token Index: 186

Text #5

Max Range: 0.2700. Min Range: -0.2700

Max Act: 0.2273. Min Act: -0.0001

Data Index: 299935 (C4 (Web Text))

Max Activating Token Index: 1018

Text #6

Max Range: 0.2700. Min Range: -0.2700

Max Act: 0.2200. Min Act: -0.0001

Data Index: 728148 (C4 (Web Text))

Max Activating Token Index: 715

Text #7

Max Range: 0.2700. Min Range: -0.2700

Max Act: 0.2088. Min Act: -0.0001

Data Index: 1120685 (C4 (Web Text))

Max Activating Token Index: 920

Text #8

Max Range: 0.2700. Min Range: -0.2700

Max Act: 0.2079. Min Act: -0.0001

Data Index: 1086133 (C4 (Web Text))

Max Activating Token Index: 541

Text #9

Max Range: 0.2700. Min Range: -0.2700

Max Act: 0.2061. Min Act: -0.0001

Data Index: 690811 (C4 (Web Text))

Max Activating Token Index: 962

Text #10

Max Range: 0.2700. Min Range: -0.2700

Max Act: 0.2028. Min Act: -0.0001

Data Index: 880460 (C4 (Web Text))

Max Activating Token Index: 866

Text #11

Max Range: 0.2700. Min Range: -0.2700

Max Act: 0.1915. Min Act: -0.0001

Data Index: 161411 (C4 (Web Text))

Max Activating Token Index: 604

Text #12

Max Range: 0.2700. Min Range: -0.2700

Max Act: 0.1975. Min Act: -0.0001

Data Index: 426333 (C4 (Web Text))

Max Activating Token Index: 765

Text #13

Max Range: 0.2700. Min Range: -0.2700

Max Act: 0.1960. Min Act: -0.0001

Data Index: 1299957 (C4 (Web Text))

Max Activating Token Index: 178

Text #14

Max Range: 0.2700. Min Range: -0.2700

Max Act: 0.1929. Min Act: -0.0001

Data Index: 707813 (C4 (Web Text))

Max Activating Token Index: 339

Text #15

Max Range: 0.2700. Min Range: -0.2700

Max Act: 0.1978. Min Act: -0.0001

Data Index: 166123 (C4 (Web Text))

Max Activating Token Index: 278

Text #16

Max Range: 0.2700. Min Range: -0.2700

Max Act: 0.1840. Min Act: -0.0001

Data Index: 343792 (C4 (Web Text))

Max Activating Token Index: 1000

Text #17

Max Range: 0.2700. Min Range: -0.2700

Max Act: 0.1774. Min Act: -0.0001

Data Index: 743404 (C4 (Web Text))

Max Activating Token Index: 997

Text #18

Max Range: 0.2700. Min Range: -0.2700

Max Act: 0.1884. Min Act: -0.0001

Data Index: 379107 (C4 (Web Text))

Max Activating Token Index: 40

Text #19

Max Range: 0.2700. Min Range: -0.2700

Max Act: 0.1895. Min Act: -0.0001

Data Index: 1314158 (C4 (Web Text))

Max Activating Token Index: 76