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

Dataset: The Pile

Neuron 1397 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: 3.2660. Min Range: -3.2660

Max Act: 3.2660. Min Act: -0.0000

Data Index: 1533081 (The Pile)

Max Activating Token Index: 8

Text #1

Max Range: 3.2660. Min Range: -3.2660

Max Act: 3.0936. Min Act: -0.0000

Data Index: 296239 (The Pile)

Max Activating Token Index: 1017

Text #2

Max Range: 3.2660. Min Range: -3.2660

Max Act: 3.0681. Min Act: -0.0000

Data Index: 571682 (The Pile)

Max Activating Token Index: 453

Text #3

Max Range: 3.2660. Min Range: -3.2660

Max Act: 3.1766. Min Act: -0.0000

Data Index: 440889 (The Pile)

Max Activating Token Index: 69

Text #4

Max Range: 3.2660. Min Range: -3.2660

Max Act: 3.1158. Min Act: -0.0000

Data Index: 160174 (The Pile)

Max Activating Token Index: 709

Text #5

Max Range: 3.2660. Min Range: -3.2660

Max Act: 2.6538. Min Act: -0.0000

Data Index: 1426655 (The Pile)

Max Activating Token Index: 412

Text #6

Max Range: 3.2660. Min Range: -3.2660

Max Act: 2.7974. Min Act: -0.0000

Data Index: 701936 (The Pile)

Max Activating Token Index: 161

Text #7

Max Range: 3.2660. Min Range: -3.2660

Max Act: 2.8804. Min Act: -0.0000

Data Index: 298552 (The Pile)

Max Activating Token Index: 263

Text #8

Max Range: 3.2660. Min Range: -3.2660

Max Act: 2.8963. Min Act: -0.0000

Data Index: 1918058 (The Pile)

Max Activating Token Index: 196

Text #9

Max Range: 3.2660. Min Range: -3.2660

Max Act: 2.5427. Min Act: -0.0000

Data Index: 1687392 (The Pile)

Max Activating Token Index: 896

Text #10

Max Range: 3.2660. Min Range: -3.2660

Max Act: 2.5942. Min Act: -0.0000

Data Index: 814217 (The Pile)

Max Activating Token Index: 18

Text #11

Max Range: 3.2660. Min Range: -3.2660

Max Act: 2.5564. Min Act: -0.0000

Data Index: 990352 (The Pile)

Max Activating Token Index: 626

Text #12

Max Range: 3.2660. Min Range: -3.2660

Max Act: 2.9054. Min Act: -0.0000

Data Index: 1084262 (The Pile)

Max Activating Token Index: 207

Text #13

Max Range: 3.2660. Min Range: -3.2660

Max Act: 2.3839. Min Act: -0.0000

Data Index: 1444892 (The Pile)

Max Activating Token Index: 935

Text #14

Max Range: 3.2660. Min Range: -3.2660

Max Act: 2.8610. Min Act: -0.0000

Data Index: 831465 (The Pile)

Max Activating Token Index: 23

Text #15

Max Range: 3.2660. Min Range: -3.2660

Max Act: 2.4630. Min Act: -0.0000

Data Index: 139574 (The Pile)

Max Activating Token Index: 235

Text #16

Max Range: 3.2660. Min Range: -3.2660

Max Act: 2.4418. Min Act: -0.0000

Data Index: 1243309 (The Pile)

Max Activating Token Index: 200

Text #17

Max Range: 3.2660. Min Range: -3.2660

Max Act: 2.8077. Min Act: -0.0000

Data Index: 1328419 (The Pile)

Max Activating Token Index: 641

Text #18

Max Range: 3.2660. Min Range: -3.2660

Max Act: 2.6464. Min Act: -0.0000

Data Index: 479657 (The Pile)

Max Activating Token Index: 392

Text #19

Max Range: 3.2660. Min Range: -3.2660

Max Act: 2.2585. Min Act: -0.0000

Data Index: 1515340 (The Pile)

Max Activating Token Index: 453