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

Dataset: The Pile

Neuron 1090 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: 1.3915. Min Range: -1.3915

Max Act: 1.3915. Min Act: -0.0000

Data Index: 975783 (The Pile)

Max Activating Token Index: 196

Text #1

Max Range: 1.3915. Min Range: -1.3915

Max Act: 1.1594. Min Act: -0.0000

Data Index: 365916 (The Pile)

Max Activating Token Index: 1017

Text #2

Max Range: 1.3915. Min Range: -1.3915

Max Act: 1.0982. Min Act: -0.0000

Data Index: 1049735 (The Pile)

Max Activating Token Index: 551

Text #3

Max Range: 1.3915. Min Range: -1.3915

Max Act: 1.0025. Min Act: -0.0000

Data Index: 1461189 (The Pile)

Max Activating Token Index: 420

Text #4

Max Range: 1.3915. Min Range: -1.3915

Max Act: 0.9731. Min Act: -0.0000

Data Index: 716115 (The Pile)

Max Activating Token Index: 133

Text #5

Max Range: 1.3915. Min Range: -1.3915

Max Act: 0.9408. Min Act: -0.0000

Data Index: 354934 (The Pile)

Max Activating Token Index: 223

Text #6

Max Range: 1.3915. Min Range: -1.3915

Max Act: 0.9787. Min Act: -0.0000

Data Index: 1283261 (The Pile)

Max Activating Token Index: 355

Text #7

Max Range: 1.3915. Min Range: -1.3915

Max Act: 1.0351. Min Act: -0.0000

Data Index: 1686816 (The Pile)

Max Activating Token Index: 198

Text #8

Max Range: 1.3915. Min Range: -1.3915

Max Act: 0.9787. Min Act: -0.0000

Data Index: 858937 (The Pile)

Max Activating Token Index: 223

Text #9

Max Range: 1.3915. Min Range: -1.3915

Max Act: 1.0414. Min Act: -0.0000

Data Index: 1024920 (The Pile)

Max Activating Token Index: 308

Text #10

Max Range: 1.3915. Min Range: -1.3915

Max Act: 0.9843. Min Act: -0.0000

Data Index: 969757 (The Pile)

Max Activating Token Index: 67

Text #11

Max Range: 1.3915. Min Range: -1.3915

Max Act: 0.9425. Min Act: -0.0000

Data Index: 1702880 (The Pile)

Max Activating Token Index: 240

Text #12

Max Range: 1.3915. Min Range: -1.3915

Max Act: 0.9151. Min Act: -0.0000

Data Index: 1043382 (The Pile)

Max Activating Token Index: 564

Text #13

Max Range: 1.3915. Min Range: -1.3915

Max Act: 0.8906. Min Act: -0.0000

Data Index: 1141137 (The Pile)

Max Activating Token Index: 95

Text #14

Max Range: 1.3915. Min Range: -1.3915

Max Act: 0.8497. Min Act: -0.0000

Data Index: 681220 (The Pile)

Max Activating Token Index: 949

Text #15

Max Range: 1.3915. Min Range: -1.3915

Max Act: 0.7955. Min Act: -0.0000

Data Index: 1897382 (The Pile)

Max Activating Token Index: 108

Text #16

Max Range: 1.3915. Min Range: -1.3915

Max Act: 0.7462. Min Act: -0.0000

Data Index: 1196231 (The Pile)

Max Activating Token Index: 906

Text #17

Max Range: 1.3915. Min Range: -1.3915

Max Act: 0.8388. Min Act: -0.0000

Data Index: 1154138 (The Pile)

Max Activating Token Index: 96

Text #18

Max Range: 1.3915. Min Range: -1.3915

Max Act: 0.8258. Min Act: -0.0000

Data Index: 1413877 (The Pile)

Max Activating Token Index: 959

Text #19

Max Range: 1.3915. Min Range: -1.3915

Max Act: 0.8045. Min Act: -0.0000

Data Index: 1923300 (The Pile)

Max Activating Token Index: 650