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

Dataset: The Pile

Neuron 2382 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1553. Min Range: -3.1553

Max Act: 3.0467. Min Act: -0.0000

Data Index: 1961800 (The Pile)

Max Activating Token Index: 900

Text #1

Max Range: 3.1553. Min Range: -3.1553

Max Act: 3.1553. Min Act: -0.0000

Data Index: 1237098 (The Pile)

Max Activating Token Index: 952

Text #2

Max Range: 3.1553. Min Range: -3.1553

Max Act: 2.9536. Min Act: -0.0000

Data Index: 240923 (The Pile)

Max Activating Token Index: 900

Text #3

Max Range: 3.1553. Min Range: -3.1553

Max Act: 2.5656. Min Act: -0.0000

Data Index: 1803269 (The Pile)

Max Activating Token Index: 297

Text #4

Max Range: 3.1553. Min Range: -3.1553

Max Act: 2.8150. Min Act: -0.0000

Data Index: 1952621 (The Pile)

Max Activating Token Index: 114

Text #5

Max Range: 3.1553. Min Range: -3.1553

Max Act: 2.6289. Min Act: -0.0000

Data Index: 776636 (The Pile)

Max Activating Token Index: 286

Text #6

Max Range: 3.1553. Min Range: -3.1553

Max Act: 2.5342. Min Act: -0.0000

Data Index: 144701 (The Pile)

Max Activating Token Index: 137

Text #7

Max Range: 3.1553. Min Range: -3.1553

Max Act: 2.5098. Min Act: -0.0000

Data Index: 1890759 (The Pile)

Max Activating Token Index: 323

Text #8

Max Range: 3.1553. Min Range: -3.1553

Max Act: 2.7338. Min Act: -0.0000

Data Index: 1302331 (The Pile)

Max Activating Token Index: 625

Text #9

Max Range: 3.1553. Min Range: -3.1553

Max Act: 2.5801. Min Act: -0.0000

Data Index: 549439 (The Pile)

Max Activating Token Index: 992

Text #10

Max Range: 3.1553. Min Range: -3.1553

Max Act: 2.1813. Min Act: -0.0000

Data Index: 1461266 (The Pile)

Max Activating Token Index: 738

Text #11

Max Range: 3.1553. Min Range: -3.1553

Max Act: 2.6085. Min Act: -0.0000

Data Index: 915765 (The Pile)

Max Activating Token Index: 899

Text #12

Max Range: 3.1553. Min Range: -3.1553

Max Act: 2.5714. Min Act: -0.0000

Data Index: 91026 (The Pile)

Max Activating Token Index: 809

Text #13

Max Range: 3.1553. Min Range: -3.1553

Max Act: 2.4805. Min Act: -0.0000

Data Index: 708666 (The Pile)

Max Activating Token Index: 242

Text #14

Max Range: 3.1553. Min Range: -3.1553

Max Act: 2.6353. Min Act: -0.0000

Data Index: 511843 (The Pile)

Max Activating Token Index: 19

Text #15

Max Range: 3.1553. Min Range: -3.1553

Max Act: 2.4450. Min Act: -0.0000

Data Index: 248470 (The Pile)

Max Activating Token Index: 867

Text #16

Max Range: 3.1553. Min Range: -3.1553

Max Act: 2.3135. Min Act: -0.0000

Data Index: 1773013 (The Pile)

Max Activating Token Index: 12

Text #17

Max Range: 3.1553. Min Range: -3.1553

Max Act: 2.4108. Min Act: -0.0000

Data Index: 59329 (The Pile)

Max Activating Token Index: 275

Text #18

Max Range: 3.1553. Min Range: -3.1553

Max Act: 2.2859. Min Act: -0.0000

Data Index: 1591632 (The Pile)

Max Activating Token Index: 211

Text #19

Max Range: 3.1553. Min Range: -3.1553

Max Act: 2.4078. Min Act: -0.0000

Data Index: 173627 (The Pile)

Max Activating Token Index: 324