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

Dataset: The Pile

Neuron 2548 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.6866. Min Act: -0.0000

Data Index: 163256 (The Pile)

Max Activating Token Index: 487

Text #1

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.6936. Min Act: -0.0000

Data Index: 623034 (The Pile)

Max Activating Token Index: 962

Text #2

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.6366. Min Act: -0.0000

Data Index: 1723572 (The Pile)

Max Activating Token Index: 280

Text #3

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.6066. Min Act: -0.0000

Data Index: 1637895 (The Pile)

Max Activating Token Index: 809

Text #4

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5776. Min Act: -0.0000

Data Index: 1443898 (The Pile)

Max Activating Token Index: 863

Text #5

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5502. Min Act: -0.0000

Data Index: 1430074 (The Pile)

Max Activating Token Index: 441

Text #6

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5205. Min Act: -0.0000

Data Index: 1631336 (The Pile)

Max Activating Token Index: 117

Text #7

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5584. Min Act: -0.0000

Data Index: 1232745 (The Pile)

Max Activating Token Index: 100

Text #8

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5756. Min Act: -0.0000

Data Index: 473847 (The Pile)

Max Activating Token Index: 156

Text #9

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5500. Min Act: -0.0000

Data Index: 1562269 (The Pile)

Max Activating Token Index: 716

Text #10

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.4821. Min Act: -0.0000

Data Index: 606676 (The Pile)

Max Activating Token Index: 835

Text #11

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5535. Min Act: -0.0000

Data Index: 1909083 (The Pile)

Max Activating Token Index: 380

Text #12

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5005. Min Act: -0.0000

Data Index: 117485 (The Pile)

Max Activating Token Index: 310

Text #13

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5010. Min Act: -0.0000

Data Index: 1130152 (The Pile)

Max Activating Token Index: 759

Text #14

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5127. Min Act: -0.0000

Data Index: 1349668 (The Pile)

Max Activating Token Index: 848

Text #15

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5147. Min Act: -0.0000

Data Index: 115492 (The Pile)

Max Activating Token Index: 701

Text #16

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5321. Min Act: -0.0000

Data Index: 903970 (The Pile)

Max Activating Token Index: 375

Text #17

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.4985. Min Act: -0.0000

Data Index: 750689 (The Pile)

Max Activating Token Index: 812

Text #18

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.4751. Min Act: -0.0000

Data Index: 1337930 (The Pile)

Max Activating Token Index: 735

Text #19

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.4991. Min Act: -0.0000

Data Index: 1771573 (The Pile)

Max Activating Token Index: 195