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

Dataset: The Pile

Neuron 4767 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: 0.8823. Min Range: -0.8823

Max Act: 0.7788. Min Act: -0.0000

Data Index: 137126 (The Pile)

Max Activating Token Index: 1000

Text #1

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.8823. Min Act: -0.0000

Data Index: 784080 (The Pile)

Max Activating Token Index: 106

Text #2

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.8179. Min Act: -0.0000

Data Index: 430485 (The Pile)

Max Activating Token Index: 183

Text #3

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.8319. Min Act: -0.0000

Data Index: 906381 (The Pile)

Max Activating Token Index: 69

Text #4

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.7887. Min Act: -0.0000

Data Index: 1800528 (The Pile)

Max Activating Token Index: 572

Text #5

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.7647. Min Act: -0.0000

Data Index: 325751 (The Pile)

Max Activating Token Index: 375

Text #6

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.7294. Min Act: -0.0000

Data Index: 1161437 (The Pile)

Max Activating Token Index: 496

Text #7

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.7565. Min Act: -0.0000

Data Index: 64403 (The Pile)

Max Activating Token Index: 750

Text #8

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.7004. Min Act: -0.0000

Data Index: 549450 (The Pile)

Max Activating Token Index: 970

Text #9

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.6485. Min Act: -0.0000

Data Index: 855554 (The Pile)

Max Activating Token Index: 814

Text #10

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.7155. Min Act: -0.0000

Data Index: 1093519 (The Pile)

Max Activating Token Index: 254

Text #11

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.6827. Min Act: -0.0000

Data Index: 1775663 (The Pile)

Max Activating Token Index: 258

Text #12

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.7461. Min Act: -0.0000

Data Index: 1229572 (The Pile)

Max Activating Token Index: 193

Text #13

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.6942. Min Act: -0.0000

Data Index: 747259 (The Pile)

Max Activating Token Index: 944

Text #14

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.7328. Min Act: -0.0000

Data Index: 1493051 (The Pile)

Max Activating Token Index: 194

Text #15

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.6626. Min Act: -0.0000

Data Index: 1360540 (The Pile)

Max Activating Token Index: 318

Text #16

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.6615. Min Act: -0.0000

Data Index: 414667 (The Pile)

Max Activating Token Index: 474

Text #17

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.7049. Min Act: -0.0000

Data Index: 1542602 (The Pile)

Max Activating Token Index: 924

Text #18

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.5824. Min Act: -0.0000

Data Index: 1608218 (The Pile)

Max Activating Token Index: 1007

Text #19

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.7008. Min Act: -0.0000

Data Index: 70349 (The Pile)

Max Activating Token Index: 878