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

Dataset: The Pile

Neuron 1377 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: 0.7576. Min Range: -0.7576

Max Act: 0.7576. Min Act: -0.0000

Data Index: 1074489 (The Pile)

Max Activating Token Index: 60

Text #1

Max Range: 0.7576. Min Range: -0.7576

Max Act: 0.5879. Min Act: -0.0000

Data Index: 1260836 (The Pile)

Max Activating Token Index: 944

Text #2

Max Range: 0.7576. Min Range: -0.7576

Max Act: 0.7164. Min Act: -0.0000

Data Index: 680500 (The Pile)

Max Activating Token Index: 757

Text #3

Max Range: 0.7576. Min Range: -0.7576

Max Act: 0.4932. Min Act: -0.0000

Data Index: 1736032 (The Pile)

Max Activating Token Index: 975

Text #4

Max Range: 0.7576. Min Range: -0.7576

Max Act: 0.4869. Min Act: -0.0000

Data Index: 337877 (The Pile)

Max Activating Token Index: 190

Text #5

Max Range: 0.7576. Min Range: -0.7576

Max Act: 0.4903. Min Act: -0.0000

Data Index: 1522290 (The Pile)

Max Activating Token Index: 72

Text #6

Max Range: 0.7576. Min Range: -0.7576

Max Act: 0.4600. Min Act: -0.0000

Data Index: 1205938 (The Pile)

Max Activating Token Index: 66

Text #7

Max Range: 0.7576. Min Range: -0.7576

Max Act: 0.4828. Min Act: -0.0000

Data Index: 1003270 (The Pile)

Max Activating Token Index: 641

Text #8

Max Range: 0.7576. Min Range: -0.7576

Max Act: 0.5017. Min Act: 0.0000

Data Index: 1125404 (The Pile)

Max Activating Token Index: 46

Text #9

Max Range: 0.7576. Min Range: -0.7576

Max Act: 0.4600. Min Act: -0.0000

Data Index: 801708 (The Pile)

Max Activating Token Index: 447

Text #10

Max Range: 0.7576. Min Range: -0.7576

Max Act: 0.3813. Min Act: -0.0000

Data Index: 344432 (The Pile)

Max Activating Token Index: 253

Text #11

Max Range: 0.7576. Min Range: -0.7576

Max Act: 0.4200. Min Act: -0.0000

Data Index: 1623499 (The Pile)

Max Activating Token Index: 641

Text #12

Max Range: 0.7576. Min Range: -0.7576

Max Act: 0.4664. Min Act: 0.0000

Data Index: 720809 (The Pile)

Max Activating Token Index: 179

Text #13

Max Range: 0.7576. Min Range: -0.7576

Max Act: 0.3729. Min Act: -0.0000

Data Index: 1488366 (The Pile)

Max Activating Token Index: 77

Text #14

Max Range: 0.7576. Min Range: -0.7576

Max Act: 0.4265. Min Act: -0.0000

Data Index: 663234 (The Pile)

Max Activating Token Index: 664

Text #15

Max Range: 0.7576. Min Range: -0.7576

Max Act: 0.4171. Min Act: -0.0000

Data Index: 763266 (The Pile)

Max Activating Token Index: 33

Text #16

Max Range: 0.7576. Min Range: -0.7576

Max Act: 0.4259. Min Act: -0.0000

Data Index: 1086159 (The Pile)

Max Activating Token Index: 513

Text #17

Max Range: 0.7576. Min Range: -0.7576

Max Act: 0.3897. Min Act: -0.0000

Data Index: 1962198 (The Pile)

Max Activating Token Index: 726

Text #18

Max Range: 0.7576. Min Range: -0.7576

Max Act: 0.4261. Min Act: -0.0000

Data Index: 1564231 (The Pile)

Max Activating Token Index: 14

Text #19

Max Range: 0.7576. Min Range: -0.7576

Max Act: 0.3930. Min Act: -0.0000

Data Index: 120027 (The Pile)

Max Activating Token Index: 90