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

Dataset: The Pile

Neuron 2686 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: 0.5159. Min Range: -0.5159

Max Act: 0.5159. Min Act: -0.0000

Data Index: 1357230 (The Pile)

Max Activating Token Index: 420

Text #1

Max Range: 0.5159. Min Range: -0.5159

Max Act: 0.4969. Min Act: -0.0000

Data Index: 880422 (The Pile)

Max Activating Token Index: 847

Text #2

Max Range: 0.5159. Min Range: -0.5159

Max Act: 0.4799. Min Act: -0.0000

Data Index: 1564744 (The Pile)

Max Activating Token Index: 872

Text #3

Max Range: 0.5159. Min Range: -0.5159

Max Act: 0.4274. Min Act: -0.0000

Data Index: 201589 (The Pile)

Max Activating Token Index: 219

Text #4

Max Range: 0.5159. Min Range: -0.5159

Max Act: 0.4237. Min Act: -0.0000

Data Index: 162378 (The Pile)

Max Activating Token Index: 281

Text #5

Max Range: 0.5159. Min Range: -0.5159

Max Act: 0.4042. Min Act: -0.0000

Data Index: 1269600 (The Pile)

Max Activating Token Index: 552

Text #6

Max Range: 0.5159. Min Range: -0.5159

Max Act: 0.4165. Min Act: -0.0000

Data Index: 598992 (The Pile)

Max Activating Token Index: 198

Text #7

Max Range: 0.5159. Min Range: -0.5159

Max Act: 0.4224. Min Act: -0.0000

Data Index: 981953 (The Pile)

Max Activating Token Index: 773

Text #8

Max Range: 0.5159. Min Range: -0.5159

Max Act: 0.4078. Min Act: -0.0000

Data Index: 1286543 (The Pile)

Max Activating Token Index: 731

Text #9

Max Range: 0.5159. Min Range: -0.5159

Max Act: 0.4174. Min Act: -0.0000

Data Index: 335376 (The Pile)

Max Activating Token Index: 957

Text #10

Max Range: 0.5159. Min Range: -0.5159

Max Act: 0.3976. Min Act: -0.0000

Data Index: 600866 (The Pile)

Max Activating Token Index: 788

Text #11

Max Range: 0.5159. Min Range: -0.5159

Max Act: 0.3765. Min Act: -0.0000

Data Index: 1447301 (The Pile)

Max Activating Token Index: 283

Text #12

Max Range: 0.5159. Min Range: -0.5159

Max Act: 0.3901. Min Act: -0.0000

Data Index: 1469006 (The Pile)

Max Activating Token Index: 193

Text #13

Max Range: 0.5159. Min Range: -0.5159

Max Act: 0.3629. Min Act: -0.0000

Data Index: 1258846 (The Pile)

Max Activating Token Index: 680

Text #14

Max Range: 0.5159. Min Range: -0.5159

Max Act: 0.3719. Min Act: -0.0000

Data Index: 1525668 (The Pile)

Max Activating Token Index: 930

Text #15

Max Range: 0.5159. Min Range: -0.5159

Max Act: 0.3800. Min Act: -0.0000

Data Index: 677945 (The Pile)

Max Activating Token Index: 128

Text #16

Max Range: 0.5159. Min Range: -0.5159

Max Act: 0.3321. Min Act: -0.0000

Data Index: 677460 (The Pile)

Max Activating Token Index: 526

Text #17

Max Range: 0.5159. Min Range: -0.5159

Max Act: 0.3880. Min Act: -0.0001

Data Index: 8721 (The Pile)

Max Activating Token Index: 652

Text #18

Max Range: 0.5159. Min Range: -0.5159

Max Act: 0.3703. Min Act: -0.0000

Data Index: 1138908 (The Pile)

Max Activating Token Index: 596

Text #19

Max Range: 0.5159. Min Range: -0.5159

Max Act: 0.3577. Min Act: -0.0000

Data Index: 1181129 (The Pile)

Max Activating Token Index: 584