Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 429 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.5214. Min Range: -0.5214

Max Act: 0.5214. Min Act: 0.0000

Data Index: 144132 (The Pile)

Max Activating Token Index: 319

Text #1

Max Range: 0.5214. Min Range: -0.5214

Max Act: 0.4874. Min Act: -0.0000

Data Index: 764144 (The Pile)

Max Activating Token Index: 60

Text #2

Max Range: 0.5214. Min Range: -0.5214

Max Act: 0.4870. Min Act: -0.0000

Data Index: 458873 (The Pile)

Max Activating Token Index: 746

Text #3

Max Range: 0.5214. Min Range: -0.5214

Max Act: 0.4704. Min Act: -0.0000

Data Index: 1434585 (The Pile)

Max Activating Token Index: 167

Text #4

Max Range: 0.5214. Min Range: -0.5214

Max Act: 0.4777. Min Act: -0.0000

Data Index: 680138 (The Pile)

Max Activating Token Index: 96

Text #5

Max Range: 0.5214. Min Range: -0.5214

Max Act: 0.4751. Min Act: -0.0000

Data Index: 766280 (The Pile)

Max Activating Token Index: 105

Text #6

Max Range: 0.5214. Min Range: -0.5214

Max Act: 0.4682. Min Act: 0.0000

Data Index: 1582234 (The Pile)

Max Activating Token Index: 85

Text #7

Max Range: 0.5214. Min Range: -0.5214

Max Act: 0.4381. Min Act: -0.0000

Data Index: 1410511 (The Pile)

Max Activating Token Index: 418

Text #8

Max Range: 0.5214. Min Range: -0.5214

Max Act: 0.4505. Min Act: 0.0000

Data Index: 512416 (The Pile)

Max Activating Token Index: 544

Text #9

Max Range: 0.5214. Min Range: -0.5214

Max Act: 0.4490. Min Act: -0.0000

Data Index: 269347 (The Pile)

Max Activating Token Index: 220

Text #10

Max Range: 0.5214. Min Range: -0.5214

Max Act: 0.4478. Min Act: 0.0000

Data Index: 1211986 (The Pile)

Max Activating Token Index: 98

Text #11

Max Range: 0.5214. Min Range: -0.5214

Max Act: 0.4456. Min Act: -0.0000

Data Index: 1431267 (The Pile)

Max Activating Token Index: 147

Text #12

Max Range: 0.5214. Min Range: -0.5214

Max Act: 0.4571. Min Act: -0.0000

Data Index: 1532026 (The Pile)

Max Activating Token Index: 131

Text #13

Max Range: 0.5214. Min Range: -0.5214

Max Act: 0.4268. Min Act: -0.0000

Data Index: 987906 (The Pile)

Max Activating Token Index: 142

Text #14

Max Range: 0.5214. Min Range: -0.5214

Max Act: 0.4391. Min Act: 0.0000

Data Index: 135633 (The Pile)

Max Activating Token Index: 174

Text #15

Max Range: 0.5214. Min Range: -0.5214

Max Act: 0.4359. Min Act: -0.0000

Data Index: 234631 (The Pile)

Max Activating Token Index: 511

Text #16

Max Range: 0.5214. Min Range: -0.5214

Max Act: 0.4218. Min Act: -0.0000

Data Index: 817935 (The Pile)

Max Activating Token Index: 131

Text #17

Max Range: 0.5214. Min Range: -0.5214

Max Act: 0.4343. Min Act: -0.0000

Data Index: 1222979 (The Pile)

Max Activating Token Index: 422

Text #18

Max Range: 0.5214. Min Range: -0.5214

Max Act: 0.4331. Min Act: -0.0000

Data Index: 130845 (The Pile)

Max Activating Token Index: 62

Text #19

Max Range: 0.5214. Min Range: -0.5214

Max Act: 0.4165. Min Act: -0.0000

Data Index: 1739496 (The Pile)

Max Activating Token Index: 639