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

Dataset: The Pile

Neuron 3919 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4320. Min Range: -1.4320

Max Act: 1.4161. Min Act: -0.0000

Data Index: 586498 (The Pile)

Max Activating Token Index: 719

Text #1

Max Range: 1.4320. Min Range: -1.4320

Max Act: 1.4320. Min Act: -0.0000

Data Index: 826677 (The Pile)

Max Activating Token Index: 575

Text #2

Max Range: 1.4320. Min Range: -1.4320

Max Act: 1.2989. Min Act: -0.0000

Data Index: 338069 (The Pile)

Max Activating Token Index: 130

Text #3

Max Range: 1.4320. Min Range: -1.4320

Max Act: 1.3255. Min Act: -0.0000

Data Index: 552679 (The Pile)

Max Activating Token Index: 494

Text #4

Max Range: 1.4320. Min Range: -1.4320

Max Act: 1.1358. Min Act: -0.0000

Data Index: 1069856 (The Pile)

Max Activating Token Index: 974

Text #5

Max Range: 1.4320. Min Range: -1.4320

Max Act: 1.1465. Min Act: -0.0000

Data Index: 1856803 (The Pile)

Max Activating Token Index: 579

Text #6

Max Range: 1.4320. Min Range: -1.4320

Max Act: 1.0540. Min Act: -0.0000

Data Index: 1704905 (The Pile)

Max Activating Token Index: 694

Text #7

Max Range: 1.4320. Min Range: -1.4320

Max Act: 1.0157. Min Act: -0.0000

Data Index: 1474421 (The Pile)

Max Activating Token Index: 647

Text #8

Max Range: 1.4320. Min Range: -1.4320

Max Act: 1.0210. Min Act: -0.0000

Data Index: 285908 (The Pile)

Max Activating Token Index: 53

Text #9

Max Range: 1.4320. Min Range: -1.4320

Max Act: 1.0061. Min Act: -0.0000

Data Index: 242600 (The Pile)

Max Activating Token Index: 876

Text #10

Max Range: 1.4320. Min Range: -1.4320

Max Act: 0.9743. Min Act: -0.0000

Data Index: 69157 (The Pile)

Max Activating Token Index: 183

Text #11

Max Range: 1.4320. Min Range: -1.4320

Max Act: 1.0939. Min Act: -0.0000

Data Index: 1367574 (The Pile)

Max Activating Token Index: 273

Text #12

Max Range: 1.4320. Min Range: -1.4320

Max Act: 0.8548. Min Act: -0.0000

Data Index: 1191928 (The Pile)

Max Activating Token Index: 377

Text #13

Max Range: 1.4320. Min Range: -1.4320

Max Act: 0.9039. Min Act: -0.0000

Data Index: 586765 (The Pile)

Max Activating Token Index: 63

Text #14

Max Range: 1.4320. Min Range: -1.4320

Max Act: 0.8989. Min Act: -0.0000

Data Index: 1547764 (The Pile)

Max Activating Token Index: 817

Text #15

Max Range: 1.4320. Min Range: -1.4320

Max Act: 0.8952. Min Act: -0.0000

Data Index: 1025363 (The Pile)

Max Activating Token Index: 640

Text #16

Max Range: 1.4320. Min Range: -1.4320

Max Act: 0.9688. Min Act: -0.0000

Data Index: 106488 (The Pile)

Max Activating Token Index: 949

Text #17

Max Range: 1.4320. Min Range: -1.4320

Max Act: 0.8512. Min Act: -0.0000

Data Index: 998396 (The Pile)

Max Activating Token Index: 1011

Text #18

Max Range: 1.4320. Min Range: -1.4320

Max Act: 0.8853. Min Act: -0.0000

Data Index: 35515 (The Pile)

Max Activating Token Index: 98

Text #19

Max Range: 1.4320. Min Range: -1.4320

Max Act: 0.8296. Min Act: -0.0000

Data Index: 225636 (The Pile)

Max Activating Token Index: 695