Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 377 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.9836. Min Range: -0.9836

Max Act: 0.9397. Min Act: -0.0000

Data Index: 1377883 (The Pile)

Max Activating Token Index: 154

Text #1

Max Range: 0.9836. Min Range: -0.9836

Max Act: 0.9836. Min Act: -0.0000

Data Index: 996348 (The Pile)

Max Activating Token Index: 885

Text #2

Max Range: 0.9836. Min Range: -0.9836

Max Act: 0.9457. Min Act: -0.0000

Data Index: 572458 (The Pile)

Max Activating Token Index: 887

Text #3

Max Range: 0.9836. Min Range: -0.9836

Max Act: 0.9319. Min Act: -0.0000

Data Index: 1629608 (The Pile)

Max Activating Token Index: 457

Text #4

Max Range: 0.9836. Min Range: -0.9836

Max Act: 0.9303. Min Act: -0.0000

Data Index: 1706202 (The Pile)

Max Activating Token Index: 943

Text #5

Max Range: 0.9836. Min Range: -0.9836

Max Act: 0.9277. Min Act: -0.0000

Data Index: 1516542 (The Pile)

Max Activating Token Index: 299

Text #6

Max Range: 0.9836. Min Range: -0.9836

Max Act: 0.8722. Min Act: -0.0000

Data Index: 195198 (The Pile)

Max Activating Token Index: 944

Text #7

Max Range: 0.9836. Min Range: -0.9836

Max Act: 0.9017. Min Act: -0.0000

Data Index: 1222984 (The Pile)

Max Activating Token Index: 998

Text #8

Max Range: 0.9836. Min Range: -0.9836

Max Act: 0.8626. Min Act: -0.0000

Data Index: 316203 (The Pile)

Max Activating Token Index: 416

Text #9

Max Range: 0.9836. Min Range: -0.9836

Max Act: 0.8881. Min Act: -0.0000

Data Index: 800810 (The Pile)

Max Activating Token Index: 426

Text #10

Max Range: 0.9836. Min Range: -0.9836

Max Act: 0.8590. Min Act: -0.0000

Data Index: 692512 (The Pile)

Max Activating Token Index: 257

Text #11

Max Range: 0.9836. Min Range: -0.9836

Max Act: 0.8821. Min Act: -0.0000

Data Index: 148531 (The Pile)

Max Activating Token Index: 921

Text #12

Max Range: 0.9836. Min Range: -0.9836

Max Act: 0.8533. Min Act: -0.0000

Data Index: 290639 (The Pile)

Max Activating Token Index: 735

Text #13

Max Range: 0.9836. Min Range: -0.9836

Max Act: 0.8739. Min Act: -0.0000

Data Index: 204879 (The Pile)

Max Activating Token Index: 167

Text #14

Max Range: 0.9836. Min Range: -0.9836

Max Act: 0.8706. Min Act: -0.0000

Data Index: 1013071 (The Pile)

Max Activating Token Index: 424

Text #15

Max Range: 0.9836. Min Range: -0.9836

Max Act: 0.8954. Min Act: -0.0001

Data Index: 1296893 (The Pile)

Max Activating Token Index: 254

Text #16

Max Range: 0.9836. Min Range: -0.9836

Max Act: 0.8136. Min Act: -0.0000

Data Index: 1764793 (The Pile)

Max Activating Token Index: 176

Text #17

Max Range: 0.9836. Min Range: -0.9836

Max Act: 0.8628. Min Act: -0.0000

Data Index: 300147 (The Pile)

Max Activating Token Index: 491

Text #18

Max Range: 0.9836. Min Range: -0.9836

Max Act: 0.8358. Min Act: -0.0000

Data Index: 700969 (The Pile)

Max Activating Token Index: 156

Text #19

Max Range: 0.9836. Min Range: -0.9836

Max Act: 0.8555. Min Act: -0.0000

Data Index: 1796402 (The Pile)

Max Activating Token Index: 139