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

Dataset: The Pile

Neuron 3900 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: 5.1994. Min Range: -5.1994

Max Act: 5.1994. Min Act: -0.0000

Data Index: 835832 (The Pile)

Max Activating Token Index: 857

Text #1

Max Range: 5.1994. Min Range: -5.1994

Max Act: 4.6932. Min Act: -0.0000

Data Index: 1568593 (The Pile)

Max Activating Token Index: 849

Text #2

Max Range: 5.1994. Min Range: -5.1994

Max Act: 4.9678. Min Act: -0.0000

Data Index: 1685416 (The Pile)

Max Activating Token Index: 272

Text #3

Max Range: 5.1994. Min Range: -5.1994

Max Act: 5.1199. Min Act: -0.0000

Data Index: 1339968 (The Pile)

Max Activating Token Index: 918

Text #4

Max Range: 5.1994. Min Range: -5.1994

Max Act: 4.9910. Min Act: -0.0000

Data Index: 758855 (The Pile)

Max Activating Token Index: 795

Text #5

Max Range: 5.1994. Min Range: -5.1994

Max Act: 4.7758. Min Act: -0.0000

Data Index: 896645 (The Pile)

Max Activating Token Index: 818

Text #6

Max Range: 5.1994. Min Range: -5.1994

Max Act: 4.6349. Min Act: -0.0000

Data Index: 100882 (The Pile)

Max Activating Token Index: 534

Text #7

Max Range: 5.1994. Min Range: -5.1994

Max Act: 4.4459. Min Act: -0.0000

Data Index: 672943 (The Pile)

Max Activating Token Index: 559

Text #8

Max Range: 5.1994. Min Range: -5.1994

Max Act: 4.2585. Min Act: -0.0000

Data Index: 1351589 (The Pile)

Max Activating Token Index: 819

Text #9

Max Range: 5.1994. Min Range: -5.1994

Max Act: 4.7562. Min Act: -0.0000

Data Index: 1284680 (The Pile)

Max Activating Token Index: 521

Text #10

Max Range: 5.1994. Min Range: -5.1994

Max Act: 4.5862. Min Act: -0.0000

Data Index: 1710040 (The Pile)

Max Activating Token Index: 931

Text #11

Max Range: 5.1994. Min Range: -5.1994

Max Act: 4.7555. Min Act: -0.0000

Data Index: 594412 (The Pile)

Max Activating Token Index: 889

Text #12

Max Range: 5.1994. Min Range: -5.1994

Max Act: 4.3954. Min Act: -0.0000

Data Index: 1339228 (The Pile)

Max Activating Token Index: 1015

Text #13

Max Range: 5.1994. Min Range: -5.1994

Max Act: 4.3659. Min Act: -0.0000

Data Index: 1800358 (The Pile)

Max Activating Token Index: 814

Text #14

Max Range: 5.1994. Min Range: -5.1994

Max Act: 4.7112. Min Act: -0.0000

Data Index: 1190236 (The Pile)

Max Activating Token Index: 175

Text #15

Max Range: 5.1994. Min Range: -5.1994

Max Act: 4.3156. Min Act: -0.0000

Data Index: 1741663 (The Pile)

Max Activating Token Index: 831

Text #16

Max Range: 5.1994. Min Range: -5.1994

Max Act: 4.4836. Min Act: -0.0000

Data Index: 1205461 (The Pile)

Max Activating Token Index: 564

Text #17

Max Range: 5.1994. Min Range: -5.1994

Max Act: 4.4320. Min Act: -0.0000

Data Index: 647037 (The Pile)

Max Activating Token Index: 487

Text #18

Max Range: 5.1994. Min Range: -5.1994

Max Act: 4.4337. Min Act: -0.0000

Data Index: 1676903 (The Pile)

Max Activating Token Index: 260

Text #19

Max Range: 5.1994. Min Range: -5.1994

Max Act: 4.4218. Min Act: -0.0000

Data Index: 1116718 (The Pile)

Max Activating Token Index: 543