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

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

Neuron 3645 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: 1.4810. Min Range: -1.4810

Max Act: 1.4473. Min Act: -0.0001

Data Index: 358348 (C4 (Web Text))

Max Activating Token Index: 274

Text #1

Max Range: 1.4810. Min Range: -1.4810

Max Act: 1.4810. Min Act: -0.0001

Data Index: 800582 (C4 (Web Text))

Max Activating Token Index: 119

Text #2

Max Range: 1.4810. Min Range: -1.4810

Max Act: 1.1873. Min Act: -0.0001

Data Index: 1143701 (C4 (Web Text))

Max Activating Token Index: 1011

Text #3

Max Range: 1.4810. Min Range: -1.4810

Max Act: 1.3365. Min Act: -0.0001

Data Index: 457283 (C4 (Web Text))

Max Activating Token Index: 764

Text #4

Max Range: 1.4810. Min Range: -1.4810

Max Act: 1.2547. Min Act: -0.0001

Data Index: 882875 (C4 (Web Text))

Max Activating Token Index: 367

Text #5

Max Range: 1.4810. Min Range: -1.4810

Max Act: 1.2141. Min Act: -0.0001

Data Index: 369680 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 1.4810. Min Range: -1.4810

Max Act: 1.3138. Min Act: -0.0001

Data Index: 748773 (C4 (Web Text))

Max Activating Token Index: 194

Text #7

Max Range: 1.4810. Min Range: -1.4810

Max Act: 1.2291. Min Act: -0.0001

Data Index: 497757 (C4 (Web Text))

Max Activating Token Index: 134

Text #8

Max Range: 1.4810. Min Range: -1.4810

Max Act: 1.1735. Min Act: -0.0001

Data Index: 1015837 (C4 (Web Text))

Max Activating Token Index: 853

Text #9

Max Range: 1.4810. Min Range: -1.4810

Max Act: 1.1661. Min Act: -0.0001

Data Index: 508296 (C4 (Web Text))

Max Activating Token Index: 179

Text #10

Max Range: 1.4810. Min Range: -1.4810

Max Act: 1.1931. Min Act: -0.0001

Data Index: 1251688 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 1.4810. Min Range: -1.4810

Max Act: 1.1234. Min Act: -0.0001

Data Index: 535174 (C4 (Web Text))

Max Activating Token Index: 598

Text #12

Max Range: 1.4810. Min Range: -1.4810

Max Act: 1.1817. Min Act: -0.0001

Data Index: 323161 (C4 (Web Text))

Max Activating Token Index: 992

Text #13

Max Range: 1.4810. Min Range: -1.4810

Max Act: 1.1771. Min Act: -0.0001

Data Index: 595299 (C4 (Web Text))

Max Activating Token Index: 403

Text #14

Max Range: 1.4810. Min Range: -1.4810

Max Act: 1.1071. Min Act: -0.0001

Data Index: 740078 (C4 (Web Text))

Max Activating Token Index: 733

Text #15

Max Range: 1.4810. Min Range: -1.4810

Max Act: 1.1697. Min Act: -0.0001

Data Index: 1145074 (C4 (Web Text))

Max Activating Token Index: 686

Text #16

Max Range: 1.4810. Min Range: -1.4810

Max Act: 1.1295. Min Act: -0.0001

Data Index: 1270561 (C4 (Web Text))

Max Activating Token Index: 926

Text #17

Max Range: 1.4810. Min Range: -1.4810

Max Act: 1.1951. Min Act: -0.0001

Data Index: 1358126 (C4 (Web Text))

Max Activating Token Index: 289

Text #18

Max Range: 1.4810. Min Range: -1.4810

Max Act: 1.1370. Min Act: -0.0001

Data Index: 1313605 (C4 (Web Text))

Max Activating Token Index: 929

Text #19

Max Range: 1.4810. Min Range: -1.4810

Max Act: 1.2935. Min Act: -0.0001

Data Index: 1350812 (C4 (Web Text))

Max Activating Token Index: 848