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

Dataset: The Pile

Neuron 2704 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3501. Min Range: -0.3501

Max Act: 0.3501. Min Act: -0.0000

Data Index: 1115523 (The Pile)

Max Activating Token Index: 670

Text #1

Max Range: 0.3501. Min Range: -0.3501

Max Act: 0.3195. Min Act: -0.0000

Data Index: 402108 (The Pile)

Max Activating Token Index: 129

Text #2

Max Range: 0.3501. Min Range: -0.3501

Max Act: 0.3442. Min Act: -0.0000

Data Index: 1835585 (The Pile)

Max Activating Token Index: 189

Text #3

Max Range: 0.3501. Min Range: -0.3501

Max Act: 0.2864. Min Act: -0.0000

Data Index: 1274902 (The Pile)

Max Activating Token Index: 153

Text #4

Max Range: 0.3501. Min Range: -0.3501

Max Act: 0.2843. Min Act: 0.0000

Data Index: 1522511 (The Pile)

Max Activating Token Index: 907

Text #5

Max Range: 0.3501. Min Range: -0.3501

Max Act: 0.2718. Min Act: -0.0000

Data Index: 856687 (The Pile)

Max Activating Token Index: 778

Text #6

Max Range: 0.3501. Min Range: -0.3501

Max Act: 0.2791. Min Act: -0.0000

Data Index: 373609 (The Pile)

Max Activating Token Index: 970

Text #7

Max Range: 0.3501. Min Range: -0.3501

Max Act: 0.3114. Min Act: -0.0000

Data Index: 343369 (The Pile)

Max Activating Token Index: 755

Text #8

Max Range: 0.3501. Min Range: -0.3501

Max Act: 0.2537. Min Act: 0.0000

Data Index: 690904 (The Pile)

Max Activating Token Index: 1015

Text #9

Max Range: 0.3501. Min Range: -0.3501

Max Act: 0.2559. Min Act: -0.0000

Data Index: 1787349 (The Pile)

Max Activating Token Index: 821

Text #10

Max Range: 0.3501. Min Range: -0.3501

Max Act: 0.2534. Min Act: 0.0000

Data Index: 1830069 (The Pile)

Max Activating Token Index: 430

Text #11

Max Range: 0.3501. Min Range: -0.3501

Max Act: 0.2476. Min Act: -0.0000

Data Index: 896838 (The Pile)

Max Activating Token Index: 715

Text #12

Max Range: 0.3501. Min Range: -0.3501

Max Act: 0.2564. Min Act: -0.0000

Data Index: 1679359 (The Pile)

Max Activating Token Index: 385

Text #13

Max Range: 0.3501. Min Range: -0.3501

Max Act: 0.2578. Min Act: -0.0000

Data Index: 1939504 (The Pile)

Max Activating Token Index: 142

Text #14

Max Range: 0.3501. Min Range: -0.3501

Max Act: 0.2612. Min Act: -0.0000

Data Index: 66248 (The Pile)

Max Activating Token Index: 657

Text #15

Max Range: 0.3501. Min Range: -0.3501

Max Act: 0.2607. Min Act: -0.0000

Data Index: 1226352 (The Pile)

Max Activating Token Index: 225

Text #16

Max Range: 0.3501. Min Range: -0.3501

Max Act: 0.2096. Min Act: -0.0000

Data Index: 1808560 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.3501. Min Range: -0.3501

Max Act: 0.2198. Min Act: -0.0000

Data Index: 1040031 (The Pile)

Max Activating Token Index: 665

Text #18

Max Range: 0.3501. Min Range: -0.3501

Max Act: 0.2394. Min Act: 0.0000

Data Index: 1709000 (The Pile)

Max Activating Token Index: 606

Text #19

Max Range: 0.3501. Min Range: -0.3501

Max Act: 0.2519. Min Act: -0.0000

Data Index: 1273632 (The Pile)

Max Activating Token Index: 112