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

Dataset: The Pile

Neuron 4403 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.5835. Min Act: -0.0000

Data Index: 1874344 (The Pile)

Max Activating Token Index: 688

Text #1

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4769. Min Act: -0.0000

Data Index: 385887 (The Pile)

Max Activating Token Index: 199

Text #2

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.5367. Min Act: -0.0000

Data Index: 1882584 (The Pile)

Max Activating Token Index: 469

Text #3

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4723. Min Act: -0.0000

Data Index: 394910 (The Pile)

Max Activating Token Index: 267

Text #4

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4580. Min Act: -0.0000

Data Index: 409610 (The Pile)

Max Activating Token Index: 276

Text #5

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4186. Min Act: -0.0000

Data Index: 573935 (The Pile)

Max Activating Token Index: 148

Text #6

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4898. Min Act: -0.0000

Data Index: 1310263 (The Pile)

Max Activating Token Index: 229

Text #7

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.3754. Min Act: -0.0000

Data Index: 1330064 (The Pile)

Max Activating Token Index: 210

Text #8

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4620. Min Act: -0.0000

Data Index: 44307 (The Pile)

Max Activating Token Index: 611

Text #9

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4023. Min Act: -0.0000

Data Index: 7230 (The Pile)

Max Activating Token Index: 871

Text #10

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4660. Min Act: -0.0000

Data Index: 1031226 (The Pile)

Max Activating Token Index: 219

Text #11

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.3968. Min Act: -0.0000

Data Index: 291107 (The Pile)

Max Activating Token Index: 96

Text #12

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4135. Min Act: -0.0000

Data Index: 1952373 (The Pile)

Max Activating Token Index: 716

Text #13

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4514. Min Act: -0.0001

Data Index: 1216152 (The Pile)

Max Activating Token Index: 832

Text #14

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.3948. Min Act: -0.0000

Data Index: 505485 (The Pile)

Max Activating Token Index: 240

Text #15

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4455. Min Act: -0.0001

Data Index: 1605286 (The Pile)

Max Activating Token Index: 9

Text #16

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4419. Min Act: -0.0001

Data Index: 1079285 (The Pile)

Max Activating Token Index: 1018

Text #17

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4440. Min Act: -0.0001

Data Index: 627786 (The Pile)

Max Activating Token Index: 104

Text #18

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4230. Min Act: -0.0000

Data Index: 526263 (The Pile)

Max Activating Token Index: 750

Text #19

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4112. Min Act: -0.0000

Data Index: 996057 (The Pile)

Max Activating Token Index: 46