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

Dataset: The Pile

Neuron 3572 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9487. Min Range: -0.9487

Max Act: 0.9487. Min Act: -0.0000

Data Index: 1056543 (The Pile)

Max Activating Token Index: 508

Text #1

Max Range: 0.9487. Min Range: -0.9487

Max Act: 0.9112. Min Act: -0.0000

Data Index: 892856 (The Pile)

Max Activating Token Index: 1008

Text #2

Max Range: 0.9487. Min Range: -0.9487

Max Act: 0.8328. Min Act: -0.0000

Data Index: 761339 (The Pile)

Max Activating Token Index: 967

Text #3

Max Range: 0.9487. Min Range: -0.9487

Max Act: 0.7767. Min Act: -0.0000

Data Index: 515771 (The Pile)

Max Activating Token Index: 673

Text #4

Max Range: 0.9487. Min Range: -0.9487

Max Act: 0.7682. Min Act: -0.0000

Data Index: 1165205 (The Pile)

Max Activating Token Index: 452

Text #5

Max Range: 0.9487. Min Range: -0.9487

Max Act: 0.7421. Min Act: -0.0000

Data Index: 1490409 (The Pile)

Max Activating Token Index: 55

Text #6

Max Range: 0.9487. Min Range: -0.9487

Max Act: 0.7256. Min Act: -0.0000

Data Index: 1578095 (The Pile)

Max Activating Token Index: 766

Text #7

Max Range: 0.9487. Min Range: -0.9487

Max Act: 0.7280. Min Act: -0.0000

Data Index: 1076750 (The Pile)

Max Activating Token Index: 201

Text #8

Max Range: 0.9487. Min Range: -0.9487

Max Act: 0.7298. Min Act: -0.0000

Data Index: 874307 (The Pile)

Max Activating Token Index: 389

Text #9

Max Range: 0.9487. Min Range: -0.9487

Max Act: 0.7023. Min Act: -0.0000

Data Index: 1804043 (The Pile)

Max Activating Token Index: 513

Text #10

Max Range: 0.9487. Min Range: -0.9487

Max Act: 0.6998. Min Act: -0.0000

Data Index: 1846268 (The Pile)

Max Activating Token Index: 267

Text #11

Max Range: 0.9487. Min Range: -0.9487

Max Act: 0.7174. Min Act: -0.0000

Data Index: 1365942 (The Pile)

Max Activating Token Index: 401

Text #12

Max Range: 0.9487. Min Range: -0.9487

Max Act: 0.7192. Min Act: -0.0000

Data Index: 853124 (The Pile)

Max Activating Token Index: 944

Text #13

Max Range: 0.9487. Min Range: -0.9487

Max Act: 0.7020. Min Act: -0.0000

Data Index: 1729270 (The Pile)

Max Activating Token Index: 422

Text #14

Max Range: 0.9487. Min Range: -0.9487

Max Act: 0.7244. Min Act: -0.0000

Data Index: 1932510 (The Pile)

Max Activating Token Index: 1004

Text #15

Max Range: 0.9487. Min Range: -0.9487

Max Act: 0.6696. Min Act: -0.0000

Data Index: 1869456 (The Pile)

Max Activating Token Index: 818

Text #16

Max Range: 0.9487. Min Range: -0.9487

Max Act: 0.6822. Min Act: -0.0000

Data Index: 1389201 (The Pile)

Max Activating Token Index: 996

Text #17

Max Range: 0.9487. Min Range: -0.9487

Max Act: 0.6580. Min Act: -0.0000

Data Index: 1331486 (The Pile)

Max Activating Token Index: 173

Text #18

Max Range: 0.9487. Min Range: -0.9487

Max Act: 0.6540. Min Act: -0.0000

Data Index: 718232 (The Pile)

Max Activating Token Index: 143

Text #19

Max Range: 0.9487. Min Range: -0.9487

Max Act: 0.6938. Min Act: -0.0000

Data Index: 1165481 (The Pile)

Max Activating Token Index: 756