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

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

Neuron 3157 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9978. Min Range: -0.9978

Max Act: 0.9978. Min Act: -0.0001

Data Index: 655785 (C4 (Web Text))

Max Activating Token Index: 254

Text #1

Max Range: 0.9978. Min Range: -0.9978

Max Act: 0.9906. Min Act: -0.0001

Data Index: 1102010 (C4 (Web Text))

Max Activating Token Index: 583

Text #2

Max Range: 0.9978. Min Range: -0.9978

Max Act: 0.9464. Min Act: -0.0001

Data Index: 1259492 (C4 (Web Text))

Max Activating Token Index: 416

Text #3

Max Range: 0.9978. Min Range: -0.9978

Max Act: 0.9092. Min Act: -0.0001

Data Index: 1243155 (C4 (Web Text))

Max Activating Token Index: 374

Text #4

Max Range: 0.9978. Min Range: -0.9978

Max Act: 0.8379. Min Act: -0.0001

Data Index: 212949 (C4 (Web Text))

Max Activating Token Index: 96

Text #5

Max Range: 0.9978. Min Range: -0.9978

Max Act: 0.8400. Min Act: -0.0001

Data Index: 766811 (C4 (Web Text))

Max Activating Token Index: 333

Text #6

Max Range: 0.9978. Min Range: -0.9978

Max Act: 0.8956. Min Act: -0.0001

Data Index: 914063 (C4 (Web Text))

Max Activating Token Index: 516

Text #7

Max Range: 0.9978. Min Range: -0.9978

Max Act: 0.8482. Min Act: -0.0001

Data Index: 1273039 (C4 (Web Text))

Max Activating Token Index: 497

Text #8

Max Range: 0.9978. Min Range: -0.9978

Max Act: 0.7970. Min Act: -0.0001

Data Index: 182679 (C4 (Web Text))

Max Activating Token Index: 215

Text #9

Max Range: 0.9978. Min Range: -0.9978

Max Act: 0.8157. Min Act: -0.0001

Data Index: 418820 (C4 (Web Text))

Max Activating Token Index: 62

Text #10

Max Range: 0.9978. Min Range: -0.9978

Max Act: 0.7717. Min Act: -0.0001

Data Index: 109898 (C4 (Web Text))

Max Activating Token Index: 30

Text #11

Max Range: 0.9978. Min Range: -0.9978

Max Act: 0.8141. Min Act: -0.0001

Data Index: 681051 (C4 (Web Text))

Max Activating Token Index: 195

Text #12

Max Range: 0.9978. Min Range: -0.9978

Max Act: 0.8141. Min Act: -0.0001

Data Index: 965785 (C4 (Web Text))

Max Activating Token Index: 1020

Text #13

Max Range: 0.9978. Min Range: -0.9978

Max Act: 0.7787. Min Act: -0.0001

Data Index: 990033 (C4 (Web Text))

Max Activating Token Index: 128

Text #14

Max Range: 0.9978. Min Range: -0.9978

Max Act: 0.7583. Min Act: -0.0001

Data Index: 953655 (C4 (Web Text))

Max Activating Token Index: 535

Text #15

Max Range: 0.9978. Min Range: -0.9978

Max Act: 0.7782. Min Act: -0.0001

Data Index: 898699 (C4 (Web Text))

Max Activating Token Index: 466

Text #16

Max Range: 0.9978. Min Range: -0.9978

Max Act: 0.7756. Min Act: -0.0001

Data Index: 1088896 (C4 (Web Text))

Max Activating Token Index: 187

Text #17

Max Range: 0.9978. Min Range: -0.9978

Max Act: 0.7566. Min Act: -0.0001

Data Index: 1224911 (C4 (Web Text))

Max Activating Token Index: 823

Text #18

Max Range: 0.9978. Min Range: -0.9978

Max Act: 0.7817. Min Act: -0.0001

Data Index: 1328061 (C4 (Web Text))

Max Activating Token Index: 213

Text #19

Max Range: 0.9978. Min Range: -0.9978

Max Act: 0.7547. Min Act: -0.0001

Data Index: 1110226 (C4 (Web Text))

Max Activating Token Index: 434