Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2299 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.9059. Min Act: -0.0000

Data Index: 848299 (The Pile)

Max Activating Token Index: 51

Text #1

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.7321. Min Act: -0.0000

Data Index: 1159335 (The Pile)

Max Activating Token Index: 290

Text #2

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.7131. Min Act: -0.0000

Data Index: 1277208 (The Pile)

Max Activating Token Index: 375

Text #3

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.6822. Min Act: -0.0000

Data Index: 1600405 (The Pile)

Max Activating Token Index: 465

Text #4

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.6912. Min Act: -0.0000

Data Index: 788104 (The Pile)

Max Activating Token Index: 415

Text #5

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.6539. Min Act: -0.0000

Data Index: 1146875 (The Pile)

Max Activating Token Index: 578

Text #6

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.6948. Min Act: -0.0000

Data Index: 224737 (The Pile)

Max Activating Token Index: 150

Text #7

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.6610. Min Act: -0.0000

Data Index: 1983154 (The Pile)

Max Activating Token Index: 418

Text #8

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.6514. Min Act: -0.0000

Data Index: 349797 (The Pile)

Max Activating Token Index: 235

Text #9

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.6254. Min Act: -0.0000

Data Index: 244510 (The Pile)

Max Activating Token Index: 537

Text #10

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.6526. Min Act: -0.0000

Data Index: 1080211 (The Pile)

Max Activating Token Index: 112

Text #11

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.6452. Min Act: -0.0000

Data Index: 588327 (The Pile)

Max Activating Token Index: 399

Text #12

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.6210. Min Act: -0.0000

Data Index: 908317 (The Pile)

Max Activating Token Index: 375

Text #13

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.5826. Min Act: -0.0000

Data Index: 589476 (The Pile)

Max Activating Token Index: 447

Text #14

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.5973. Min Act: -0.0000

Data Index: 1417183 (The Pile)

Max Activating Token Index: 120

Text #15

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.5608. Min Act: -0.0000

Data Index: 1930195 (The Pile)

Max Activating Token Index: 333

Text #16

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.6113. Min Act: -0.0000

Data Index: 962398 (The Pile)

Max Activating Token Index: 557

Text #17

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.6175. Min Act: -0.0000

Data Index: 1517355 (The Pile)

Max Activating Token Index: 563

Text #18

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.5897. Min Act: -0.0000

Data Index: 791160 (The Pile)

Max Activating Token Index: 759

Text #19

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.5909. Min Act: -0.0000

Data Index: 1268314 (The Pile)

Max Activating Token Index: 85