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

Dataset: The Pile

Neuron 1340 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9180. Min Range: -0.9180

Max Act: 0.9180. Min Act: -0.0000

Data Index: 1305696 (The Pile)

Max Activating Token Index: 233

Text #1

Max Range: 0.9180. Min Range: -0.9180

Max Act: 0.7687. Min Act: -0.0000

Data Index: 564587 (The Pile)

Max Activating Token Index: 242

Text #2

Max Range: 0.9180. Min Range: -0.9180

Max Act: 0.6731. Min Act: -0.0000

Data Index: 546963 (The Pile)

Max Activating Token Index: 130

Text #3

Max Range: 0.9180. Min Range: -0.9180

Max Act: 0.6866. Min Act: -0.0000

Data Index: 916444 (The Pile)

Max Activating Token Index: 444

Text #4

Max Range: 0.9180. Min Range: -0.9180

Max Act: 0.6785. Min Act: -0.0000

Data Index: 1284640 (The Pile)

Max Activating Token Index: 359

Text #5

Max Range: 0.9180. Min Range: -0.9180

Max Act: 0.6584. Min Act: -0.0000

Data Index: 80054 (The Pile)

Max Activating Token Index: 283

Text #6

Max Range: 0.9180. Min Range: -0.9180

Max Act: 0.6940. Min Act: -0.0000

Data Index: 1913402 (The Pile)

Max Activating Token Index: 449

Text #7

Max Range: 0.9180. Min Range: -0.9180

Max Act: 0.6506. Min Act: -0.0000

Data Index: 1150499 (The Pile)

Max Activating Token Index: 796

Text #8

Max Range: 0.9180. Min Range: -0.9180

Max Act: 0.6610. Min Act: -0.0000

Data Index: 1740890 (The Pile)

Max Activating Token Index: 696

Text #9

Max Range: 0.9180. Min Range: -0.9180

Max Act: 0.6266. Min Act: -0.0000

Data Index: 1273259 (The Pile)

Max Activating Token Index: 130

Text #10

Max Range: 0.9180. Min Range: -0.9180

Max Act: 0.6477. Min Act: -0.0000

Data Index: 1806914 (The Pile)

Max Activating Token Index: 879

Text #11

Max Range: 0.9180. Min Range: -0.9180

Max Act: 0.6129. Min Act: -0.0000

Data Index: 886934 (The Pile)

Max Activating Token Index: 118

Text #12

Max Range: 0.9180. Min Range: -0.9180

Max Act: 0.6343. Min Act: -0.0000

Data Index: 68611 (The Pile)

Max Activating Token Index: 303

Text #13

Max Range: 0.9180. Min Range: -0.9180

Max Act: 0.6323. Min Act: -0.0000

Data Index: 1893194 (The Pile)

Max Activating Token Index: 180

Text #14

Max Range: 0.9180. Min Range: -0.9180

Max Act: 0.6416. Min Act: -0.0000

Data Index: 1334715 (The Pile)

Max Activating Token Index: 137

Text #15

Max Range: 0.9180. Min Range: -0.9180

Max Act: 0.6234. Min Act: -0.0000

Data Index: 1571008 (The Pile)

Max Activating Token Index: 853

Text #16

Max Range: 0.9180. Min Range: -0.9180

Max Act: 0.6217. Min Act: -0.0000

Data Index: 377845 (The Pile)

Max Activating Token Index: 883

Text #17

Max Range: 0.9180. Min Range: -0.9180

Max Act: 0.6074. Min Act: -0.0000

Data Index: 360285 (The Pile)

Max Activating Token Index: 247

Text #18

Max Range: 0.9180. Min Range: -0.9180

Max Act: 0.6241. Min Act: -0.0000

Data Index: 815073 (The Pile)

Max Activating Token Index: 97

Text #19

Max Range: 0.9180. Min Range: -0.9180

Max Act: 0.5990. Min Act: -0.0000

Data Index: 1348911 (The Pile)

Max Activating Token Index: 677