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

Dataset: The Pile

Neuron 1298 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: 0.8128. Min Range: -0.8128

Max Act: 0.8128. Min Act: -0.0000

Data Index: 254984 (The Pile)

Max Activating Token Index: 714

Text #1

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.8031. Min Act: -0.0000

Data Index: 1851604 (The Pile)

Max Activating Token Index: 432

Text #2

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.7967. Min Act: -0.0000

Data Index: 77622 (The Pile)

Max Activating Token Index: 650

Text #3

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.7716. Min Act: -0.0000

Data Index: 1146720 (The Pile)

Max Activating Token Index: 789

Text #4

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.7352. Min Act: -0.0000

Data Index: 677375 (The Pile)

Max Activating Token Index: 418

Text #5

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.7097. Min Act: -0.0000

Data Index: 1716622 (The Pile)

Max Activating Token Index: 557

Text #6

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.7510. Min Act: -0.0000

Data Index: 559297 (The Pile)

Max Activating Token Index: 448

Text #7

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.7246. Min Act: -0.0000

Data Index: 1202285 (The Pile)

Max Activating Token Index: 513

Text #8

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.7567. Min Act: -0.0000

Data Index: 1191922 (The Pile)

Max Activating Token Index: 534

Text #9

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.7651. Min Act: -0.0000

Data Index: 1615683 (The Pile)

Max Activating Token Index: 395

Text #10

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.7133. Min Act: -0.0000

Data Index: 1088381 (The Pile)

Max Activating Token Index: 65

Text #11

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.7503. Min Act: -0.0000

Data Index: 276062 (The Pile)

Max Activating Token Index: 670

Text #12

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.7267. Min Act: -0.0000

Data Index: 57743 (The Pile)

Max Activating Token Index: 464

Text #13

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.7279. Min Act: -0.0000

Data Index: 941121 (The Pile)

Max Activating Token Index: 834

Text #14

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.7249. Min Act: -0.0000

Data Index: 1493227 (The Pile)

Max Activating Token Index: 805

Text #15

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.7399. Min Act: -0.0000

Data Index: 387803 (The Pile)

Max Activating Token Index: 557

Text #16

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.7385. Min Act: -0.0000

Data Index: 247408 (The Pile)

Max Activating Token Index: 115

Text #17

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.7423. Min Act: -0.0000

Data Index: 429176 (The Pile)

Max Activating Token Index: 984

Text #18

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.7365. Min Act: -0.0000

Data Index: 77544 (The Pile)

Max Activating Token Index: 763

Text #19

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.7585. Min Act: 0.0000

Data Index: 1873125 (The Pile)

Max Activating Token Index: 122