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

Dataset: The Pile

Neuron 3497 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: 3.2241. Min Range: -3.2241

Max Act: 3.0584. Min Act: -0.0000

Data Index: 210137 (The Pile)

Max Activating Token Index: 917

Text #1

Max Range: 3.2241. Min Range: -3.2241

Max Act: 2.8024. Min Act: -0.0000

Data Index: 1536445 (The Pile)

Max Activating Token Index: 479

Text #2

Max Range: 3.2241. Min Range: -3.2241

Max Act: 2.8034. Min Act: -0.0000

Data Index: 692483 (The Pile)

Max Activating Token Index: 1017

Text #3

Max Range: 3.2241. Min Range: -3.2241

Max Act: 3.0172. Min Act: -0.0000

Data Index: 1918449 (The Pile)

Max Activating Token Index: 178

Text #4

Max Range: 3.2241. Min Range: -3.2241

Max Act: 3.1194. Min Act: -0.0000

Data Index: 863178 (The Pile)

Max Activating Token Index: 951

Text #5

Max Range: 3.2241. Min Range: -3.2241

Max Act: 3.1727. Min Act: -0.0000

Data Index: 791737 (The Pile)

Max Activating Token Index: 688

Text #6

Max Range: 3.2241. Min Range: -3.2241

Max Act: 3.2241. Min Act: -0.0000

Data Index: 1854774 (The Pile)

Max Activating Token Index: 827

Text #7

Max Range: 3.2241. Min Range: -3.2241

Max Act: 2.8947. Min Act: -0.0000

Data Index: 1378737 (The Pile)

Max Activating Token Index: 433

Text #8

Max Range: 3.2241. Min Range: -3.2241

Max Act: 2.8167. Min Act: -0.0000

Data Index: 828472 (The Pile)

Max Activating Token Index: 525

Text #9

Max Range: 3.2241. Min Range: -3.2241

Max Act: 2.8042. Min Act: -0.0000

Data Index: 58801 (The Pile)

Max Activating Token Index: 87

Text #10

Max Range: 3.2241. Min Range: -3.2241

Max Act: 2.7144. Min Act: -0.0000

Data Index: 1097715 (The Pile)

Max Activating Token Index: 912

Text #11

Max Range: 3.2241. Min Range: -3.2241

Max Act: 2.9198. Min Act: -0.0000

Data Index: 1398281 (The Pile)

Max Activating Token Index: 333

Text #12

Max Range: 3.2241. Min Range: -3.2241

Max Act: 2.4706. Min Act: -0.0000

Data Index: 1548724 (The Pile)

Max Activating Token Index: 1010

Text #13

Max Range: 3.2241. Min Range: -3.2241

Max Act: 3.1423. Min Act: -0.0000

Data Index: 1713778 (The Pile)

Max Activating Token Index: 365

Text #14

Max Range: 3.2241. Min Range: -3.2241

Max Act: 2.6895. Min Act: -0.0000

Data Index: 1886940 (The Pile)

Max Activating Token Index: 869

Text #15

Max Range: 3.2241. Min Range: -3.2241

Max Act: 2.9004. Min Act: -0.0000

Data Index: 1655144 (The Pile)

Max Activating Token Index: 882

Text #16

Max Range: 3.2241. Min Range: -3.2241

Max Act: 3.0004. Min Act: -0.0000

Data Index: 1594466 (The Pile)

Max Activating Token Index: 39

Text #17

Max Range: 3.2241. Min Range: -3.2241

Max Act: 2.6405. Min Act: -0.0000

Data Index: 1635733 (The Pile)

Max Activating Token Index: 650

Text #18

Max Range: 3.2241. Min Range: -3.2241

Max Act: 2.6945. Min Act: -0.0000

Data Index: 264196 (The Pile)

Max Activating Token Index: 859

Text #19

Max Range: 3.2241. Min Range: -3.2241

Max Act: 2.8406. Min Act: -0.0000

Data Index: 1427608 (The Pile)

Max Activating Token Index: 918