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

Dataset: The Pile

Neuron 1859 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5300. Min Range: -1.5300

Max Act: 1.5199. Min Act: -0.0000

Data Index: 1956511 (The Pile)

Max Activating Token Index: 540

Text #1

Max Range: 1.5300. Min Range: -1.5300

Max Act: 1.5300. Min Act: -0.0000

Data Index: 1203161 (The Pile)

Max Activating Token Index: 854

Text #2

Max Range: 1.5300. Min Range: -1.5300

Max Act: 1.3598. Min Act: -0.0001

Data Index: 5918 (The Pile)

Max Activating Token Index: 778

Text #3

Max Range: 1.5300. Min Range: -1.5300

Max Act: 1.3868. Min Act: -0.0000

Data Index: 707202 (The Pile)

Max Activating Token Index: 412

Text #4

Max Range: 1.5300. Min Range: -1.5300

Max Act: 1.3866. Min Act: -0.0000

Data Index: 1885225 (The Pile)

Max Activating Token Index: 184

Text #5

Max Range: 1.5300. Min Range: -1.5300

Max Act: 1.3101. Min Act: -0.0000

Data Index: 1156609 (The Pile)

Max Activating Token Index: 683

Text #6

Max Range: 1.5300. Min Range: -1.5300

Max Act: 1.4314. Min Act: -0.0000

Data Index: 73701 (The Pile)

Max Activating Token Index: 665

Text #7

Max Range: 1.5300. Min Range: -1.5300

Max Act: 1.3306. Min Act: -0.0000

Data Index: 71138 (The Pile)

Max Activating Token Index: 666

Text #8

Max Range: 1.5300. Min Range: -1.5300

Max Act: 1.3352. Min Act: -0.0000

Data Index: 1172990 (The Pile)

Max Activating Token Index: 983

Text #9

Max Range: 1.5300. Min Range: -1.5300

Max Act: 1.2866. Min Act: -0.0000

Data Index: 722569 (The Pile)

Max Activating Token Index: 726

Text #10

Max Range: 1.5300. Min Range: -1.5300

Max Act: 1.3552. Min Act: -0.0000

Data Index: 1830954 (The Pile)

Max Activating Token Index: 90

Text #11

Max Range: 1.5300. Min Range: -1.5300

Max Act: 1.2461. Min Act: -0.0000

Data Index: 904056 (The Pile)

Max Activating Token Index: 537

Text #12

Max Range: 1.5300. Min Range: -1.5300

Max Act: 1.2718. Min Act: -0.0000

Data Index: 1917646 (The Pile)

Max Activating Token Index: 127

Text #13

Max Range: 1.5300. Min Range: -1.5300

Max Act: 1.2513. Min Act: 0.0000

Data Index: 896542 (The Pile)

Max Activating Token Index: 178

Text #14

Max Range: 1.5300. Min Range: -1.5300

Max Act: 1.1928. Min Act: -0.0000

Data Index: 1617890 (The Pile)

Max Activating Token Index: 542

Text #15

Max Range: 1.5300. Min Range: -1.5300

Max Act: 1.2480. Min Act: -0.0000

Data Index: 1985503 (The Pile)

Max Activating Token Index: 376

Text #16

Max Range: 1.5300. Min Range: -1.5300

Max Act: 1.1693. Min Act: -0.0000

Data Index: 1268914 (The Pile)

Max Activating Token Index: 298

Text #17

Max Range: 1.5300. Min Range: -1.5300

Max Act: 1.2367. Min Act: -0.0000

Data Index: 1353921 (The Pile)

Max Activating Token Index: 465

Text #18

Max Range: 1.5300. Min Range: -1.5300

Max Act: 1.2155. Min Act: -0.0000

Data Index: 863409 (The Pile)

Max Activating Token Index: 418

Text #19

Max Range: 1.5300. Min Range: -1.5300

Max Act: 1.2539. Min Act: -0.0000

Data Index: 1797935 (The Pile)

Max Activating Token Index: 183