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

Dataset: The Pile

Neuron 1389 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: 0.5963. Min Range: -0.5963

Max Act: 0.5963. Min Act: -0.0000

Data Index: 916777 (The Pile)

Max Activating Token Index: 332

Text #1

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.5877. Min Act: -0.0000

Data Index: 319993 (The Pile)

Max Activating Token Index: 629

Text #2

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.5486. Min Act: -0.0000

Data Index: 1425153 (The Pile)

Max Activating Token Index: 60

Text #3

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.5210. Min Act: -0.0000

Data Index: 1661428 (The Pile)

Max Activating Token Index: 886

Text #4

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4762. Min Act: -0.0000

Data Index: 963755 (The Pile)

Max Activating Token Index: 529

Text #5

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4987. Min Act: -0.0000

Data Index: 588498 (The Pile)

Max Activating Token Index: 471

Text #6

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4638. Min Act: -0.0000

Data Index: 1039994 (The Pile)

Max Activating Token Index: 832

Text #7

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4397. Min Act: -0.0000

Data Index: 1752954 (The Pile)

Max Activating Token Index: 838

Text #8

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4297. Min Act: -0.0000

Data Index: 225473 (The Pile)

Max Activating Token Index: 886

Text #9

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4428. Min Act: -0.0000

Data Index: 1424588 (The Pile)

Max Activating Token Index: 282

Text #10

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4142. Min Act: -0.0000

Data Index: 418091 (The Pile)

Max Activating Token Index: 980

Text #11

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4382. Min Act: -0.0000

Data Index: 555219 (The Pile)

Max Activating Token Index: 622

Text #12

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4250. Min Act: -0.0000

Data Index: 1999736 (The Pile)

Max Activating Token Index: 57

Text #13

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4143. Min Act: -0.0000

Data Index: 329476 (The Pile)

Max Activating Token Index: 290

Text #14

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4146. Min Act: -0.0000

Data Index: 1864810 (The Pile)

Max Activating Token Index: 492

Text #15

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4106. Min Act: -0.0000

Data Index: 488216 (The Pile)

Max Activating Token Index: 322

Text #16

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.3888. Min Act: -0.0000

Data Index: 398819 (The Pile)

Max Activating Token Index: 457

Text #17

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4110. Min Act: -0.0000

Data Index: 192674 (The Pile)

Max Activating Token Index: 161

Text #18

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4006. Min Act: -0.0000

Data Index: 1566022 (The Pile)

Max Activating Token Index: 313

Text #19

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.3785. Min Act: -0.0000

Data Index: 1268623 (The Pile)

Max Activating Token Index: 997