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

Dataset: The Pile

Neuron 1602 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: 3.0559. Min Range: -3.0559

Max Act: 3.0559. Min Act: -0.0000

Data Index: 1436710 (The Pile)

Max Activating Token Index: 1013

Text #1

Max Range: 3.0559. Min Range: -3.0559

Max Act: 2.6160. Min Act: -0.0000

Data Index: 177313 (The Pile)

Max Activating Token Index: 454

Text #2

Max Range: 3.0559. Min Range: -3.0559

Max Act: 2.7326. Min Act: -0.0000

Data Index: 651374 (The Pile)

Max Activating Token Index: 61

Text #3

Max Range: 3.0559. Min Range: -3.0559

Max Act: 2.7184. Min Act: -0.0000

Data Index: 297033 (The Pile)

Max Activating Token Index: 119

Text #4

Max Range: 3.0559. Min Range: -3.0559

Max Act: 2.1882. Min Act: -0.0000

Data Index: 1441387 (The Pile)

Max Activating Token Index: 964

Text #5

Max Range: 3.0559. Min Range: -3.0559

Max Act: 2.3971. Min Act: -0.0000

Data Index: 760134 (The Pile)

Max Activating Token Index: 336

Text #6

Max Range: 3.0559. Min Range: -3.0559

Max Act: 2.4422. Min Act: -0.0000

Data Index: 503981 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 3.0559. Min Range: -3.0559

Max Act: 2.2978. Min Act: -0.0000

Data Index: 1272641 (The Pile)

Max Activating Token Index: 623

Text #8

Max Range: 3.0559. Min Range: -3.0559

Max Act: 2.0954. Min Act: -0.0000

Data Index: 1512149 (The Pile)

Max Activating Token Index: 359

Text #9

Max Range: 3.0559. Min Range: -3.0559

Max Act: 2.1657. Min Act: -0.0000

Data Index: 430117 (The Pile)

Max Activating Token Index: 774

Text #10

Max Range: 3.0559. Min Range: -3.0559

Max Act: 2.1617. Min Act: -0.0000

Data Index: 731290 (The Pile)

Max Activating Token Index: 114

Text #11

Max Range: 3.0559. Min Range: -3.0559

Max Act: 2.1554. Min Act: -0.0000

Data Index: 1299921 (The Pile)

Max Activating Token Index: 195

Text #12

Max Range: 3.0559. Min Range: -3.0559

Max Act: 2.0415. Min Act: -0.0000

Data Index: 340737 (The Pile)

Max Activating Token Index: 117

Text #13

Max Range: 3.0559. Min Range: -3.0559

Max Act: 2.2808. Min Act: -0.0000

Data Index: 1506566 (The Pile)

Max Activating Token Index: 278

Text #14

Max Range: 3.0559. Min Range: -3.0559

Max Act: 2.2501. Min Act: -0.0000

Data Index: 1343990 (The Pile)

Max Activating Token Index: 827

Text #15

Max Range: 3.0559. Min Range: -3.0559

Max Act: 2.1006. Min Act: -0.0000

Data Index: 574236 (The Pile)

Max Activating Token Index: 851

Text #16

Max Range: 3.0559. Min Range: -3.0559

Max Act: 1.8979. Min Act: -0.0000

Data Index: 902115 (The Pile)

Max Activating Token Index: 680

Text #17

Max Range: 3.0559. Min Range: -3.0559

Max Act: 2.0854. Min Act: -0.0000

Data Index: 241713 (The Pile)

Max Activating Token Index: 312

Text #18

Max Range: 3.0559. Min Range: -3.0559

Max Act: 1.9670. Min Act: -0.0000

Data Index: 1812817 (The Pile)

Max Activating Token Index: 511

Text #19

Max Range: 3.0559. Min Range: -3.0559

Max Act: 2.0760. Min Act: -0.0000

Data Index: 1799622 (The Pile)

Max Activating Token Index: 980