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

Dataset: The Pile

Neuron 3861 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.7586. Min Act: -0.0000

Data Index: 838630 (The Pile)

Max Activating Token Index: 150

Text #1

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.7003. Min Act: -0.0000

Data Index: 1378927 (The Pile)

Max Activating Token Index: 515

Text #2

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.6794. Min Act: -0.0000

Data Index: 1376123 (The Pile)

Max Activating Token Index: 210

Text #3

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.6958. Min Act: -0.0000

Data Index: 97292 (The Pile)

Max Activating Token Index: 164

Text #4

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.5833. Min Act: -0.0000

Data Index: 408365 (The Pile)

Max Activating Token Index: 92

Text #5

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.6614. Min Act: -0.0000

Data Index: 1791115 (The Pile)

Max Activating Token Index: 308

Text #6

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.5526. Min Act: -0.0000

Data Index: 760010 (The Pile)

Max Activating Token Index: 188

Text #7

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.6351. Min Act: -0.0000

Data Index: 87570 (The Pile)

Max Activating Token Index: 300

Text #8

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.6494. Min Act: -0.0000

Data Index: 114786 (The Pile)

Max Activating Token Index: 478

Text #9

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.6039. Min Act: -0.0000

Data Index: 452956 (The Pile)

Max Activating Token Index: 846

Text #10

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.5984. Min Act: -0.0000

Data Index: 30157 (The Pile)

Max Activating Token Index: 744

Text #11

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.6144. Min Act: -0.0000

Data Index: 644133 (The Pile)

Max Activating Token Index: 620

Text #12

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.5846. Min Act: -0.0000

Data Index: 1849550 (The Pile)

Max Activating Token Index: 222

Text #13

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.6153. Min Act: -0.0000

Data Index: 48609 (The Pile)

Max Activating Token Index: 487

Text #14

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.6150. Min Act: -0.0000

Data Index: 235800 (The Pile)

Max Activating Token Index: 540

Text #15

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.5649. Min Act: -0.0000

Data Index: 1306929 (The Pile)

Max Activating Token Index: 392

Text #16

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.5868. Min Act: -0.0000

Data Index: 480665 (The Pile)

Max Activating Token Index: 992

Text #17

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.6040. Min Act: -0.0000

Data Index: 1367791 (The Pile)

Max Activating Token Index: 85

Text #18

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.5878. Min Act: -0.0000

Data Index: 1880063 (The Pile)

Max Activating Token Index: 632

Text #19

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.5185. Min Act: -0.0000

Data Index: 230410 (The Pile)

Max Activating Token Index: 398