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

Dataset: The Pile

Neuron 2975 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0288. Min Range: -1.0288

Max Act: 1.0288. Min Act: -0.0000

Data Index: 1857536 (The Pile)

Max Activating Token Index: 460

Text #1

Max Range: 1.0288. Min Range: -1.0288

Max Act: 1.0040. Min Act: -0.0000

Data Index: 1147046 (The Pile)

Max Activating Token Index: 313

Text #2

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.9036. Min Act: -0.0000

Data Index: 338825 (The Pile)

Max Activating Token Index: 195

Text #3

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.8919. Min Act: -0.0000

Data Index: 768334 (The Pile)

Max Activating Token Index: 290

Text #4

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.8371. Min Act: -0.0000

Data Index: 1218570 (The Pile)

Max Activating Token Index: 979

Text #5

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.8880. Min Act: -0.0000

Data Index: 1724319 (The Pile)

Max Activating Token Index: 158

Text #6

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.8064. Min Act: -0.0000

Data Index: 842274 (The Pile)

Max Activating Token Index: 296

Text #7

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.7295. Min Act: -0.0000

Data Index: 967245 (The Pile)

Max Activating Token Index: 804

Text #8

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.7755. Min Act: -0.0000

Data Index: 730694 (The Pile)

Max Activating Token Index: 457

Text #9

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.8261. Min Act: -0.0000

Data Index: 1960440 (The Pile)

Max Activating Token Index: 253

Text #10

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.7532. Min Act: -0.0000

Data Index: 1190673 (The Pile)

Max Activating Token Index: 415

Text #11

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.7299. Min Act: -0.0000

Data Index: 1635060 (The Pile)

Max Activating Token Index: 244

Text #12

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.7214. Min Act: -0.0000

Data Index: 1711587 (The Pile)

Max Activating Token Index: 754

Text #13

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.7526. Min Act: -0.0000

Data Index: 372981 (The Pile)

Max Activating Token Index: 608

Text #14

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.6824. Min Act: -0.0000

Data Index: 1988742 (The Pile)

Max Activating Token Index: 937

Text #15

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.7052. Min Act: -0.0000

Data Index: 1307776 (The Pile)

Max Activating Token Index: 239

Text #16

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.6323. Min Act: -0.0000

Data Index: 833801 (The Pile)

Max Activating Token Index: 993

Text #17

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.6602. Min Act: -0.0000

Data Index: 767590 (The Pile)

Max Activating Token Index: 471

Text #18

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.6442. Min Act: -0.0000

Data Index: 1708892 (The Pile)

Max Activating Token Index: 147

Text #19

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.6531. Min Act: -0.0000

Data Index: 841118 (The Pile)

Max Activating Token Index: 502