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

Dataset: The Pile

Neuron 1318 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: 1.6712. Min Range: -1.6712

Max Act: 1.6217. Min Act: -0.0000

Data Index: 235719 (The Pile)

Max Activating Token Index: 434

Text #1

Max Range: 1.6712. Min Range: -1.6712

Max Act: 1.6712. Min Act: -0.0000

Data Index: 1876845 (The Pile)

Max Activating Token Index: 518

Text #2

Max Range: 1.6712. Min Range: -1.6712

Max Act: 1.4460. Min Act: -0.0000

Data Index: 1056540 (The Pile)

Max Activating Token Index: 602

Text #3

Max Range: 1.6712. Min Range: -1.6712

Max Act: 1.4088. Min Act: -0.0000

Data Index: 70658 (The Pile)

Max Activating Token Index: 118

Text #4

Max Range: 1.6712. Min Range: -1.6712

Max Act: 1.5084. Min Act: -0.0000

Data Index: 1989781 (The Pile)

Max Activating Token Index: 267

Text #5

Max Range: 1.6712. Min Range: -1.6712

Max Act: 1.5139. Min Act: -0.0000

Data Index: 791135 (The Pile)

Max Activating Token Index: 374

Text #6

Max Range: 1.6712. Min Range: -1.6712

Max Act: 1.3190. Min Act: -0.0000

Data Index: 1606222 (The Pile)

Max Activating Token Index: 362

Text #7

Max Range: 1.6712. Min Range: -1.6712

Max Act: 1.4022. Min Act: -0.0000

Data Index: 1538738 (The Pile)

Max Activating Token Index: 664

Text #8

Max Range: 1.6712. Min Range: -1.6712

Max Act: 1.4853. Min Act: -0.0000

Data Index: 308527 (The Pile)

Max Activating Token Index: 524

Text #9

Max Range: 1.6712. Min Range: -1.6712

Max Act: 1.3377. Min Act: -0.0000

Data Index: 41131 (The Pile)

Max Activating Token Index: 840

Text #10

Max Range: 1.6712. Min Range: -1.6712

Max Act: 1.4213. Min Act: -0.0000

Data Index: 224136 (The Pile)

Max Activating Token Index: 617

Text #11

Max Range: 1.6712. Min Range: -1.6712

Max Act: 1.1939. Min Act: -0.0000

Data Index: 1474688 (The Pile)

Max Activating Token Index: 666

Text #12

Max Range: 1.6712. Min Range: -1.6712

Max Act: 1.2858. Min Act: -0.0000

Data Index: 150262 (The Pile)

Max Activating Token Index: 852

Text #13

Max Range: 1.6712. Min Range: -1.6712

Max Act: 1.3209. Min Act: -0.0000

Data Index: 1792812 (The Pile)

Max Activating Token Index: 153

Text #14

Max Range: 1.6712. Min Range: -1.6712

Max Act: 1.2673. Min Act: -0.0000

Data Index: 1704481 (The Pile)

Max Activating Token Index: 738

Text #15

Max Range: 1.6712. Min Range: -1.6712

Max Act: 1.3617. Min Act: -0.0000

Data Index: 1975532 (The Pile)

Max Activating Token Index: 467

Text #16

Max Range: 1.6712. Min Range: -1.6712

Max Act: 1.1946. Min Act: -0.0000

Data Index: 1977726 (The Pile)

Max Activating Token Index: 462

Text #17

Max Range: 1.6712. Min Range: -1.6712

Max Act: 1.3718. Min Act: -0.0000

Data Index: 143033 (The Pile)

Max Activating Token Index: 618

Text #18

Max Range: 1.6712. Min Range: -1.6712

Max Act: 1.2361. Min Act: -0.0000

Data Index: 1527276 (The Pile)

Max Activating Token Index: 86

Text #19

Max Range: 1.6712. Min Range: -1.6712

Max Act: 1.3235. Min Act: -0.0000

Data Index: 407277 (The Pile)

Max Activating Token Index: 485