Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4491 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.3960. Min Range: -1.3960

Max Act: 1.3960. Min Act: -0.0000

Data Index: 1586735 (The Pile)

Max Activating Token Index: 614

Text #1

Max Range: 1.3960. Min Range: -1.3960

Max Act: 1.2468. Min Act: -0.0000

Data Index: 802101 (The Pile)

Max Activating Token Index: 325

Text #2

Max Range: 1.3960. Min Range: -1.3960

Max Act: 1.2352. Min Act: -0.0000

Data Index: 312790 (The Pile)

Max Activating Token Index: 42

Text #3

Max Range: 1.3960. Min Range: -1.3960

Max Act: 1.1168. Min Act: -0.0000

Data Index: 1077583 (The Pile)

Max Activating Token Index: 108

Text #4

Max Range: 1.3960. Min Range: -1.3960

Max Act: 1.1067. Min Act: -0.0000

Data Index: 194007 (The Pile)

Max Activating Token Index: 394

Text #5

Max Range: 1.3960. Min Range: -1.3960

Max Act: 1.2289. Min Act: -0.0000

Data Index: 150496 (The Pile)

Max Activating Token Index: 534

Text #6

Max Range: 1.3960. Min Range: -1.3960

Max Act: 1.1451. Min Act: -0.0000

Data Index: 1450950 (The Pile)

Max Activating Token Index: 691

Text #7

Max Range: 1.3960. Min Range: -1.3960

Max Act: 1.2435. Min Act: -0.0000

Data Index: 307073 (The Pile)

Max Activating Token Index: 652

Text #8

Max Range: 1.3960. Min Range: -1.3960

Max Act: 1.2076. Min Act: -0.0000

Data Index: 1765425 (The Pile)

Max Activating Token Index: 990

Text #9

Max Range: 1.3960. Min Range: -1.3960

Max Act: 1.1291. Min Act: -0.0000

Data Index: 1235937 (The Pile)

Max Activating Token Index: 117

Text #10

Max Range: 1.3960. Min Range: -1.3960

Max Act: 1.1203. Min Act: -0.0000

Data Index: 32863 (The Pile)

Max Activating Token Index: 964

Text #11

Max Range: 1.3960. Min Range: -1.3960

Max Act: 1.0662. Min Act: -0.0000

Data Index: 222934 (The Pile)

Max Activating Token Index: 334

Text #12

Max Range: 1.3960. Min Range: -1.3960

Max Act: 1.0847. Min Act: -0.0000

Data Index: 921683 (The Pile)

Max Activating Token Index: 168

Text #13

Max Range: 1.3960. Min Range: -1.3960

Max Act: 1.0301. Min Act: -0.0000

Data Index: 107315 (The Pile)

Max Activating Token Index: 212

Text #14

Max Range: 1.3960. Min Range: -1.3960

Max Act: 1.0467. Min Act: -0.0000

Data Index: 542029 (The Pile)

Max Activating Token Index: 567

Text #15

Max Range: 1.3960. Min Range: -1.3960

Max Act: 1.1020. Min Act: -0.0000

Data Index: 883898 (The Pile)

Max Activating Token Index: 947

Text #16

Max Range: 1.3960. Min Range: -1.3960

Max Act: 1.0432. Min Act: -0.0000

Data Index: 1144933 (The Pile)

Max Activating Token Index: 648

Text #17

Max Range: 1.3960. Min Range: -1.3960

Max Act: 1.0471. Min Act: -0.0000

Data Index: 1427943 (The Pile)

Max Activating Token Index: 340

Text #18

Max Range: 1.3960. Min Range: -1.3960

Max Act: 1.0799. Min Act: -0.0000

Data Index: 1228026 (The Pile)

Max Activating Token Index: 598

Text #19

Max Range: 1.3960. Min Range: -1.3960

Max Act: 1.1342. Min Act: -0.0000

Data Index: 1637075 (The Pile)

Max Activating Token Index: 679