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

Dataset: The Pile

Neuron 2444 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: 0.6332. Min Range: -0.6332

Max Act: 0.6332. Min Act: -0.0000

Data Index: 692599 (The Pile)

Max Activating Token Index: 898

Text #1

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.5998. Min Act: -0.0000

Data Index: 1158315 (The Pile)

Max Activating Token Index: 175

Text #2

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.5342. Min Act: -0.0000

Data Index: 1870767 (The Pile)

Max Activating Token Index: 543

Text #3

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.5283. Min Act: -0.0000

Data Index: 1600369 (The Pile)

Max Activating Token Index: 241

Text #4

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.4728. Min Act: -0.0000

Data Index: 688265 (The Pile)

Max Activating Token Index: 778

Text #5

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.5112. Min Act: -0.0000

Data Index: 1419301 (The Pile)

Max Activating Token Index: 40

Text #6

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.4616. Min Act: -0.0000

Data Index: 1823104 (The Pile)

Max Activating Token Index: 796

Text #7

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.5219. Min Act: -0.0000

Data Index: 1468617 (The Pile)

Max Activating Token Index: 906

Text #8

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.5213. Min Act: -0.0000

Data Index: 1011458 (The Pile)

Max Activating Token Index: 600

Text #9

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.5138. Min Act: -0.0000

Data Index: 59475 (The Pile)

Max Activating Token Index: 907

Text #10

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.5012. Min Act: -0.0000

Data Index: 1490211 (The Pile)

Max Activating Token Index: 529

Text #11

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.4575. Min Act: -0.0000

Data Index: 1371317 (The Pile)

Max Activating Token Index: 237

Text #12

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.4666. Min Act: -0.0000

Data Index: 6268 (The Pile)

Max Activating Token Index: 829

Text #13

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.5087. Min Act: -0.0000

Data Index: 519705 (The Pile)

Max Activating Token Index: 721

Text #14

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.4552. Min Act: -0.0000

Data Index: 995652 (The Pile)

Max Activating Token Index: 872

Text #15

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.4416. Min Act: -0.0000

Data Index: 1969991 (The Pile)

Max Activating Token Index: 646

Text #16

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.4572. Min Act: -0.0000

Data Index: 1108253 (The Pile)

Max Activating Token Index: 358

Text #17

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.4382. Min Act: -0.0000

Data Index: 1103754 (The Pile)

Max Activating Token Index: 68

Text #18

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.4530. Min Act: -0.0000

Data Index: 1565190 (The Pile)

Max Activating Token Index: 114

Text #19

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.4230. Min Act: -0.0000

Data Index: 1225455 (The Pile)

Max Activating Token Index: 281