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

Dataset: The Pile

Neuron 1145 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.5277. Min Act: -0.0000

Data Index: 1216931 (The Pile)

Max Activating Token Index: 773

Text #1

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.4761. Min Act: -0.0000

Data Index: 173906 (The Pile)

Max Activating Token Index: 331

Text #2

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.4568. Min Act: -0.0000

Data Index: 1058836 (The Pile)

Max Activating Token Index: 726

Text #3

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.4771. Min Act: -0.0000

Data Index: 212515 (The Pile)

Max Activating Token Index: 103

Text #4

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.4649. Min Act: -0.0000

Data Index: 1375321 (The Pile)

Max Activating Token Index: 948

Text #5

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.4695. Min Act: -0.0000

Data Index: 314797 (The Pile)

Max Activating Token Index: 887

Text #6

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.4461. Min Act: -0.0000

Data Index: 98752 (The Pile)

Max Activating Token Index: 108

Text #7

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.3883. Min Act: -0.0000

Data Index: 196720 (The Pile)

Max Activating Token Index: 98

Text #8

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.3968. Min Act: -0.0000

Data Index: 1184219 (The Pile)

Max Activating Token Index: 568

Text #9

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.3986. Min Act: -0.0000

Data Index: 784882 (The Pile)

Max Activating Token Index: 987

Text #10

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.4044. Min Act: -0.0000

Data Index: 559983 (The Pile)

Max Activating Token Index: 483

Text #11

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.4091. Min Act: -0.0000

Data Index: 1336772 (The Pile)

Max Activating Token Index: 735

Text #12

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.4234. Min Act: -0.0000

Data Index: 494144 (The Pile)

Max Activating Token Index: 466

Text #13

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.3913. Min Act: -0.0000

Data Index: 1065584 (The Pile)

Max Activating Token Index: 362

Text #14

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.3711. Min Act: -0.0000

Data Index: 234248 (The Pile)

Max Activating Token Index: 9

Text #15

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.3920. Min Act: -0.0000

Data Index: 186524 (The Pile)

Max Activating Token Index: 1021

Text #16

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.3821. Min Act: -0.0000

Data Index: 731731 (The Pile)

Max Activating Token Index: 349

Text #17

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.3751. Min Act: -0.0000

Data Index: 322032 (The Pile)

Max Activating Token Index: 171

Text #18

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.3547. Min Act: -0.0000

Data Index: 39828 (The Pile)

Max Activating Token Index: 108

Text #19

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.3772. Min Act: -0.0000

Data Index: 1656819 (The Pile)

Max Activating Token Index: 177