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

Dataset: The Pile

Neuron 1164 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.5162. Min Act: -0.0000

Data Index: 1337767 (The Pile)

Max Activating Token Index: 19

Text #1

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.5162. Min Act: -0.0000

Data Index: 618944 (The Pile)

Max Activating Token Index: 225

Text #2

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.5052. Min Act: -0.0000

Data Index: 1949808 (The Pile)

Max Activating Token Index: 999

Text #3

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4688. Min Act: -0.0000

Data Index: 1488525 (The Pile)

Max Activating Token Index: 581

Text #4

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4671. Min Act: -0.0000

Data Index: 715854 (The Pile)

Max Activating Token Index: 524

Text #5

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4584. Min Act: -0.0000

Data Index: 244703 (The Pile)

Max Activating Token Index: 227

Text #6

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4429. Min Act: -0.0000

Data Index: 817702 (The Pile)

Max Activating Token Index: 577

Text #7

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4466. Min Act: -0.0000

Data Index: 592847 (The Pile)

Max Activating Token Index: 297

Text #8

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4342. Min Act: -0.0000

Data Index: 155338 (The Pile)

Max Activating Token Index: 351

Text #9

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4504. Min Act: -0.0000

Data Index: 137481 (The Pile)

Max Activating Token Index: 353

Text #10

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4514. Min Act: -0.0000

Data Index: 692533 (The Pile)

Max Activating Token Index: 865

Text #11

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4344. Min Act: -0.0000

Data Index: 962198 (The Pile)

Max Activating Token Index: 198

Text #12

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4390. Min Act: -0.0000

Data Index: 88128 (The Pile)

Max Activating Token Index: 229

Text #13

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4337. Min Act: -0.0000

Data Index: 1190398 (The Pile)

Max Activating Token Index: 309

Text #14

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4215. Min Act: -0.0000

Data Index: 674069 (The Pile)

Max Activating Token Index: 961

Text #15

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4103. Min Act: -0.0000

Data Index: 1108886 (The Pile)

Max Activating Token Index: 632

Text #16

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.3649. Min Act: -0.0000

Data Index: 1191785 (The Pile)

Max Activating Token Index: 731

Text #17

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.3725. Min Act: -0.0000

Data Index: 198801 (The Pile)

Max Activating Token Index: 614

Text #18

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4004. Min Act: -0.0000

Data Index: 1659812 (The Pile)

Max Activating Token Index: 148

Text #19

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.3489. Min Act: -0.0000

Data Index: 941706 (The Pile)

Max Activating Token Index: 587