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

Dataset: The Pile

Neuron 1047 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8236. Min Range: -3.8236

Max Act: 3.8236. Min Act: -0.0000

Data Index: 178076 (The Pile)

Max Activating Token Index: 469

Text #1

Max Range: 3.8236. Min Range: -3.8236

Max Act: 3.5253. Min Act: -0.0000

Data Index: 1920304 (The Pile)

Max Activating Token Index: 578

Text #2

Max Range: 3.8236. Min Range: -3.8236

Max Act: 3.5130. Min Act: -0.0000

Data Index: 752178 (The Pile)

Max Activating Token Index: 101

Text #3

Max Range: 3.8236. Min Range: -3.8236

Max Act: 3.3656. Min Act: -0.0000

Data Index: 92492 (The Pile)

Max Activating Token Index: 1016

Text #4

Max Range: 3.8236. Min Range: -3.8236

Max Act: 3.0386. Min Act: -0.0000

Data Index: 1519268 (The Pile)

Max Activating Token Index: 818

Text #5

Max Range: 3.8236. Min Range: -3.8236

Max Act: 3.0228. Min Act: -0.0000

Data Index: 1345760 (The Pile)

Max Activating Token Index: 540

Text #6

Max Range: 3.8236. Min Range: -3.8236

Max Act: 2.9744. Min Act: -0.0000

Data Index: 1129520 (The Pile)

Max Activating Token Index: 342

Text #7

Max Range: 3.8236. Min Range: -3.8236

Max Act: 2.9437. Min Act: -0.0000

Data Index: 914629 (The Pile)

Max Activating Token Index: 879

Text #8

Max Range: 3.8236. Min Range: -3.8236

Max Act: 2.8229. Min Act: -0.0000

Data Index: 1087246 (The Pile)

Max Activating Token Index: 859

Text #9

Max Range: 3.8236. Min Range: -3.8236

Max Act: 2.9481. Min Act: -0.0000

Data Index: 469669 (The Pile)

Max Activating Token Index: 88

Text #10

Max Range: 3.8236. Min Range: -3.8236

Max Act: 2.9549. Min Act: -0.0000

Data Index: 1165535 (The Pile)

Max Activating Token Index: 834

Text #11

Max Range: 3.8236. Min Range: -3.8236

Max Act: 2.9073. Min Act: -0.0000

Data Index: 1806936 (The Pile)

Max Activating Token Index: 705

Text #12

Max Range: 3.8236. Min Range: -3.8236

Max Act: 2.8732. Min Act: -0.0000

Data Index: 1649135 (The Pile)

Max Activating Token Index: 237

Text #13

Max Range: 3.8236. Min Range: -3.8236

Max Act: 2.8673. Min Act: -0.0000

Data Index: 1284252 (The Pile)

Max Activating Token Index: 699

Text #14

Max Range: 3.8236. Min Range: -3.8236

Max Act: 2.8013. Min Act: -0.0000

Data Index: 572373 (The Pile)

Max Activating Token Index: 407

Text #15

Max Range: 3.8236. Min Range: -3.8236

Max Act: 2.7750. Min Act: -0.0000

Data Index: 881472 (The Pile)

Max Activating Token Index: 197

Text #16

Max Range: 3.8236. Min Range: -3.8236

Max Act: 2.5481. Min Act: -0.0000

Data Index: 1936409 (The Pile)

Max Activating Token Index: 79

Text #17

Max Range: 3.8236. Min Range: -3.8236

Max Act: 2.8063. Min Act: -0.0000

Data Index: 462696 (The Pile)

Max Activating Token Index: 20

Text #18

Max Range: 3.8236. Min Range: -3.8236

Max Act: 2.6655. Min Act: -0.0000

Data Index: 42728 (The Pile)

Max Activating Token Index: 964

Text #19

Max Range: 3.8236. Min Range: -3.8236

Max Act: 2.6291. Min Act: -0.0000

Data Index: 677580 (The Pile)

Max Activating Token Index: 121