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

Dataset: The Pile

Neuron 149 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9269. Min Range: -0.9269

Max Act: 0.9269. Min Act: -0.0000

Data Index: 951627 (The Pile)

Max Activating Token Index: 667

Text #1

Max Range: 0.9269. Min Range: -0.9269

Max Act: 0.7167. Min Act: -0.0000

Data Index: 441068 (The Pile)

Max Activating Token Index: 213

Text #2

Max Range: 0.9269. Min Range: -0.9269

Max Act: 0.7033. Min Act: -0.0000

Data Index: 1240639 (The Pile)

Max Activating Token Index: 157

Text #3

Max Range: 0.9269. Min Range: -0.9269

Max Act: 0.6447. Min Act: -0.0000

Data Index: 621667 (The Pile)

Max Activating Token Index: 142

Text #4

Max Range: 0.9269. Min Range: -0.9269

Max Act: 0.7470. Min Act: -0.0000

Data Index: 710373 (The Pile)

Max Activating Token Index: 119

Text #5

Max Range: 0.9269. Min Range: -0.9269

Max Act: 0.6935. Min Act: -0.0000

Data Index: 938423 (The Pile)

Max Activating Token Index: 330

Text #6

Max Range: 0.9269. Min Range: -0.9269

Max Act: 0.6701. Min Act: -0.0000

Data Index: 882276 (The Pile)

Max Activating Token Index: 59

Text #7

Max Range: 0.9269. Min Range: -0.9269

Max Act: 0.6685. Min Act: -0.0000

Data Index: 126414 (The Pile)

Max Activating Token Index: 599

Text #8

Max Range: 0.9269. Min Range: -0.9269

Max Act: 0.6477. Min Act: -0.0000

Data Index: 925591 (The Pile)

Max Activating Token Index: 468

Text #9

Max Range: 0.9269. Min Range: -0.9269

Max Act: 0.6590. Min Act: -0.0000

Data Index: 453784 (The Pile)

Max Activating Token Index: 126

Text #10

Max Range: 0.9269. Min Range: -0.9269

Max Act: 0.6927. Min Act: -0.0000

Data Index: 143873 (The Pile)

Max Activating Token Index: 588

Text #11

Max Range: 0.9269. Min Range: -0.9269

Max Act: 0.6183. Min Act: -0.0000

Data Index: 1560563 (The Pile)

Max Activating Token Index: 268

Text #12

Max Range: 0.9269. Min Range: -0.9269

Max Act: 0.6542. Min Act: -0.0000

Data Index: 981003 (The Pile)

Max Activating Token Index: 463

Text #13

Max Range: 0.9269. Min Range: -0.9269

Max Act: 0.6771. Min Act: -0.0000

Data Index: 605640 (The Pile)

Max Activating Token Index: 208

Text #14

Max Range: 0.9269. Min Range: -0.9269

Max Act: 0.6588. Min Act: -0.0000

Data Index: 986082 (The Pile)

Max Activating Token Index: 139

Text #15

Max Range: 0.9269. Min Range: -0.9269

Max Act: 0.6315. Min Act: -0.0000

Data Index: 120634 (The Pile)

Max Activating Token Index: 592

Text #16

Max Range: 0.9269. Min Range: -0.9269

Max Act: 0.6312. Min Act: -0.0000

Data Index: 1341559 (The Pile)

Max Activating Token Index: 291

Text #17

Max Range: 0.9269. Min Range: -0.9269

Max Act: 0.6516. Min Act: -0.0000

Data Index: 554123 (The Pile)

Max Activating Token Index: 134

Text #18

Max Range: 0.9269. Min Range: -0.9269

Max Act: 0.6255. Min Act: -0.0000

Data Index: 1447723 (The Pile)

Max Activating Token Index: 736

Text #19

Max Range: 0.9269. Min Range: -0.9269

Max Act: 0.6224. Min Act: -0.0000

Data Index: 1408510 (The Pile)

Max Activating Token Index: 995