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

Dataset: The Pile

Neuron 3575 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5261. Min Range: -1.5261

Max Act: 1.5261. Min Act: -0.0000

Data Index: 1849380 (The Pile)

Max Activating Token Index: 694

Text #1

Max Range: 1.5261. Min Range: -1.5261

Max Act: 1.2109. Min Act: -0.0000

Data Index: 729784 (The Pile)

Max Activating Token Index: 1007

Text #2

Max Range: 1.5261. Min Range: -1.5261

Max Act: 1.4532. Min Act: -0.0000

Data Index: 1575217 (The Pile)

Max Activating Token Index: 911

Text #3

Max Range: 1.5261. Min Range: -1.5261

Max Act: 1.4048. Min Act: -0.0000

Data Index: 1952583 (The Pile)

Max Activating Token Index: 29

Text #4

Max Range: 1.5261. Min Range: -1.5261

Max Act: 1.4191. Min Act: -0.0000

Data Index: 432979 (The Pile)

Max Activating Token Index: 373

Text #5

Max Range: 1.5261. Min Range: -1.5261

Max Act: 1.2355. Min Act: -0.0000

Data Index: 144474 (The Pile)

Max Activating Token Index: 966

Text #6

Max Range: 1.5261. Min Range: -1.5261

Max Act: 1.3262. Min Act: -0.0000

Data Index: 772867 (The Pile)

Max Activating Token Index: 523

Text #7

Max Range: 1.5261. Min Range: -1.5261

Max Act: 1.2755. Min Act: -0.0000

Data Index: 1701601 (The Pile)

Max Activating Token Index: 415

Text #8

Max Range: 1.5261. Min Range: -1.5261

Max Act: 1.1644. Min Act: -0.0000

Data Index: 595782 (The Pile)

Max Activating Token Index: 465

Text #9

Max Range: 1.5261. Min Range: -1.5261

Max Act: 1.2942. Min Act: -0.0000

Data Index: 723084 (The Pile)

Max Activating Token Index: 673

Text #10

Max Range: 1.5261. Min Range: -1.5261

Max Act: 1.2227. Min Act: -0.0000

Data Index: 1849030 (The Pile)

Max Activating Token Index: 142

Text #11

Max Range: 1.5261. Min Range: -1.5261

Max Act: 1.2986. Min Act: -0.0000

Data Index: 651361 (The Pile)

Max Activating Token Index: 838

Text #12

Max Range: 1.5261. Min Range: -1.5261

Max Act: 1.1510. Min Act: -0.0000

Data Index: 382165 (The Pile)

Max Activating Token Index: 687

Text #13

Max Range: 1.5261. Min Range: -1.5261

Max Act: 1.1213. Min Act: -0.0000

Data Index: 1437653 (The Pile)

Max Activating Token Index: 439

Text #14

Max Range: 1.5261. Min Range: -1.5261

Max Act: 1.1499. Min Act: -0.0000

Data Index: 281644 (The Pile)

Max Activating Token Index: 894

Text #15

Max Range: 1.5261. Min Range: -1.5261

Max Act: 1.1425. Min Act: -0.0000

Data Index: 981335 (The Pile)

Max Activating Token Index: 362

Text #16

Max Range: 1.5261. Min Range: -1.5261

Max Act: 1.2009. Min Act: -0.0000

Data Index: 1298923 (The Pile)

Max Activating Token Index: 339

Text #17

Max Range: 1.5261. Min Range: -1.5261

Max Act: 1.0092. Min Act: -0.0000

Data Index: 1772873 (The Pile)

Max Activating Token Index: 153

Text #18

Max Range: 1.5261. Min Range: -1.5261

Max Act: 1.1217. Min Act: -0.0000

Data Index: 1200144 (The Pile)

Max Activating Token Index: 8

Text #19

Max Range: 1.5261. Min Range: -1.5261

Max Act: 1.0025. Min Act: -0.0000

Data Index: 8247 (The Pile)

Max Activating Token Index: 931