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

Dataset: The Pile

Neuron 1594 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.8476. Min Act: -0.0000

Data Index: 1517712 (The Pile)

Max Activating Token Index: 172

Text #1

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.7954. Min Act: -0.0000

Data Index: 265694 (The Pile)

Max Activating Token Index: 499

Text #2

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.6788. Min Act: -0.0000

Data Index: 478214 (The Pile)

Max Activating Token Index: 566

Text #3

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.6816. Min Act: -0.0000

Data Index: 1515853 (The Pile)

Max Activating Token Index: 203

Text #4

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.6830. Min Act: -0.0000

Data Index: 900382 (The Pile)

Max Activating Token Index: 105

Text #5

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.7549. Min Act: -0.0000

Data Index: 1547126 (The Pile)

Max Activating Token Index: 304

Text #6

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.4957. Min Act: -0.0000

Data Index: 961544 (The Pile)

Max Activating Token Index: 165

Text #7

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.6324. Min Act: -0.0000

Data Index: 1375201 (The Pile)

Max Activating Token Index: 65

Text #8

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.5656. Min Act: -0.0000

Data Index: 1352686 (The Pile)

Max Activating Token Index: 548

Text #9

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.5881. Min Act: -0.0000

Data Index: 1309725 (The Pile)

Max Activating Token Index: 473

Text #10

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.5161. Min Act: -0.0000

Data Index: 76476 (The Pile)

Max Activating Token Index: 811

Text #11

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.5173. Min Act: -0.0000

Data Index: 555874 (The Pile)

Max Activating Token Index: 569

Text #12

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.4667. Min Act: -0.0000

Data Index: 1321136 (The Pile)

Max Activating Token Index: 538

Text #13

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.3560. Min Act: -0.0000

Data Index: 1108094 (The Pile)

Max Activating Token Index: 748

Text #14

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.4288. Min Act: -0.0000

Data Index: 552801 (The Pile)

Max Activating Token Index: 912

Text #15

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.3115. Min Act: -0.0000

Data Index: 469474 (The Pile)

Max Activating Token Index: 136

Text #16

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.4107. Min Act: -0.0000

Data Index: 1652157 (The Pile)

Max Activating Token Index: 369

Text #17

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.3649. Min Act: -0.0000

Data Index: 560170 (The Pile)

Max Activating Token Index: 653

Text #18

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.3903. Min Act: -0.0000

Data Index: 265519 (The Pile)

Max Activating Token Index: 217

Text #19

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.3773. Min Act: -0.0000

Data Index: 1472527 (The Pile)

Max Activating Token Index: 281