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

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

Neuron 1626 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: 3.3034. Min Range: -3.3034

Max Act: 3.3034. Min Act: -0.0001

Data Index: 695953 (C4 (Web Text))

Max Activating Token Index: 208

Text #1

Max Range: 3.3034. Min Range: -3.3034

Max Act: 3.2612. Min Act: -0.0001

Data Index: 711163 (C4 (Web Text))

Max Activating Token Index: 118

Text #2

Max Range: 3.3034. Min Range: -3.3034

Max Act: 2.9879. Min Act: -0.0001

Data Index: 184191 (C4 (Web Text))

Max Activating Token Index: 247

Text #3

Max Range: 3.3034. Min Range: -3.3034

Max Act: 2.7741. Min Act: -0.0001

Data Index: 193445 (C4 (Web Text))

Max Activating Token Index: 838

Text #4

Max Range: 3.3034. Min Range: -3.3034

Max Act: 3.0671. Min Act: -0.0000

Data Index: 742095 (C4 (Web Text))

Max Activating Token Index: 327

Text #5

Max Range: 3.3034. Min Range: -3.3034

Max Act: 2.9863. Min Act: -0.0001

Data Index: 1077419 (C4 (Web Text))

Max Activating Token Index: 443

Text #6

Max Range: 3.3034. Min Range: -3.3034

Max Act: 2.6849. Min Act: -0.0001

Data Index: 542521 (C4 (Web Text))

Max Activating Token Index: 833

Text #7

Max Range: 3.3034. Min Range: -3.3034

Max Act: 2.7683. Min Act: -0.0001

Data Index: 1110467 (C4 (Web Text))

Max Activating Token Index: 465

Text #8

Max Range: 3.3034. Min Range: -3.3034

Max Act: 1.8969. Min Act: -0.0001

Data Index: 657482 (C4 (Web Text))

Max Activating Token Index: 104

Text #9

Max Range: 3.3034. Min Range: -3.3034

Max Act: 2.6765. Min Act: -0.0001

Data Index: 1270736 (C4 (Web Text))

Max Activating Token Index: 826

Text #10

Max Range: 3.3034. Min Range: -3.3034

Max Act: 2.4010. Min Act: -0.0001

Data Index: 273045 (C4 (Web Text))

Max Activating Token Index: 56

Text #11

Max Range: 3.3034. Min Range: -3.3034

Max Act: 2.8461. Min Act: -0.0000

Data Index: 871310 (C4 (Web Text))

Max Activating Token Index: 912

Text #12

Max Range: 3.3034. Min Range: -3.3034

Max Act: 2.8588. Min Act: -0.0001

Data Index: 722610 (C4 (Web Text))

Max Activating Token Index: 273

Text #13

Max Range: 3.3034. Min Range: -3.3034

Max Act: 2.5034. Min Act: -0.0000

Data Index: 602874 (C4 (Web Text))

Max Activating Token Index: 387

Text #14

Max Range: 3.3034. Min Range: -3.3034

Max Act: 2.7091. Min Act: -0.0001

Data Index: 1053334 (C4 (Web Text))

Max Activating Token Index: 992

Text #15

Max Range: 3.3034. Min Range: -3.3034

Max Act: 2.5143. Min Act: -0.0001

Data Index: 1547889 (Python Code)

Max Activating Token Index: 502

Text #16

Max Range: 3.3034. Min Range: -3.3034

Max Act: 2.5159. Min Act: -0.0001

Data Index: 1642716 (Python Code)

Max Activating Token Index: 677

Text #17

Max Range: 3.3034. Min Range: -3.3034

Max Act: 2.3272. Min Act: -0.0001

Data Index: 318860 (C4 (Web Text))

Max Activating Token Index: 1016

Text #18

Max Range: 3.3034. Min Range: -3.3034

Max Act: 2.3398. Min Act: -0.0001

Data Index: 931925 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 3.3034. Min Range: -3.3034

Max Act: 2.4349. Min Act: -0.0001

Data Index: 768283 (C4 (Web Text))

Max Activating Token Index: 246