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

Dataset: The Pile

Neuron 2734 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.4533. Min Range: -0.4533

Max Act: 0.4533. Min Act: -0.0000

Data Index: 1126953 (The Pile)

Max Activating Token Index: 817

Text #1

Max Range: 0.4533. Min Range: -0.4533

Max Act: 0.4198. Min Act: -0.0000

Data Index: 640571 (The Pile)

Max Activating Token Index: 855

Text #2

Max Range: 0.4533. Min Range: -0.4533

Max Act: 0.4051. Min Act: -0.0000

Data Index: 1495804 (The Pile)

Max Activating Token Index: 390

Text #3

Max Range: 0.4533. Min Range: -0.4533

Max Act: 0.3921. Min Act: -0.0000

Data Index: 675704 (The Pile)

Max Activating Token Index: 842

Text #4

Max Range: 0.4533. Min Range: -0.4533

Max Act: 0.3494. Min Act: -0.0000

Data Index: 964458 (The Pile)

Max Activating Token Index: 441

Text #5

Max Range: 0.4533. Min Range: -0.4533

Max Act: 0.3330. Min Act: -0.0000

Data Index: 792035 (The Pile)

Max Activating Token Index: 693

Text #6

Max Range: 0.4533. Min Range: -0.4533

Max Act: 0.2942. Min Act: -0.0000

Data Index: 1550103 (The Pile)

Max Activating Token Index: 34

Text #7

Max Range: 0.4533. Min Range: -0.4533

Max Act: 0.3144. Min Act: -0.0000

Data Index: 269582 (The Pile)

Max Activating Token Index: 146

Text #8

Max Range: 0.4533. Min Range: -0.4533

Max Act: 0.3160. Min Act: -0.0000

Data Index: 1124970 (The Pile)

Max Activating Token Index: 82

Text #9

Max Range: 0.4533. Min Range: -0.4533

Max Act: 0.3038. Min Act: -0.0000

Data Index: 185380 (The Pile)

Max Activating Token Index: 533

Text #10

Max Range: 0.4533. Min Range: -0.4533

Max Act: 0.2889. Min Act: -0.0000

Data Index: 62728 (The Pile)

Max Activating Token Index: 723

Text #11

Max Range: 0.4533. Min Range: -0.4533

Max Act: 0.3117. Min Act: -0.0001

Data Index: 1689299 (The Pile)

Max Activating Token Index: 242

Text #12

Max Range: 0.4533. Min Range: -0.4533

Max Act: 0.2991. Min Act: -0.0000

Data Index: 1011700 (The Pile)

Max Activating Token Index: 698

Text #13

Max Range: 0.4533. Min Range: -0.4533

Max Act: 0.2734. Min Act: -0.0000

Data Index: 170868 (The Pile)

Max Activating Token Index: 723

Text #14

Max Range: 0.4533. Min Range: -0.4533

Max Act: 0.2934. Min Act: -0.0000

Data Index: 534530 (The Pile)

Max Activating Token Index: 544

Text #15

Max Range: 0.4533. Min Range: -0.4533

Max Act: 0.2895. Min Act: -0.0000

Data Index: 1489363 (The Pile)

Max Activating Token Index: 414

Text #16

Max Range: 0.4533. Min Range: -0.4533

Max Act: 0.2592. Min Act: -0.0000

Data Index: 528744 (The Pile)

Max Activating Token Index: 712

Text #17

Max Range: 0.4533. Min Range: -0.4533

Max Act: 0.2761. Min Act: -0.0000

Data Index: 43681 (The Pile)

Max Activating Token Index: 422

Text #18

Max Range: 0.4533. Min Range: -0.4533

Max Act: 0.2860. Min Act: -0.0000

Data Index: 97874 (The Pile)

Max Activating Token Index: 375

Text #19

Max Range: 0.4533. Min Range: -0.4533

Max Act: 0.3062. Min Act: -0.0000

Data Index: 1393450 (The Pile)

Max Activating Token Index: 23