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

Dataset: The Pile

Neuron 2631 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5216. Min Range: -5.5216

Max Act: 5.5216. Min Act: -0.0000

Data Index: 48196 (The Pile)

Max Activating Token Index: 853

Text #1

Max Range: 5.5216. Min Range: -5.5216

Max Act: 5.3663. Min Act: -0.0000

Data Index: 716955 (The Pile)

Max Activating Token Index: 57

Text #2

Max Range: 5.5216. Min Range: -5.5216

Max Act: 5.0091. Min Act: -0.0000

Data Index: 15889 (The Pile)

Max Activating Token Index: 86

Text #3

Max Range: 5.5216. Min Range: -5.5216

Max Act: 4.9164. Min Act: -0.0000

Data Index: 1243807 (The Pile)

Max Activating Token Index: 44

Text #4

Max Range: 5.5216. Min Range: -5.5216

Max Act: 4.7019. Min Act: -0.0000

Data Index: 980155 (The Pile)

Max Activating Token Index: 43

Text #5

Max Range: 5.5216. Min Range: -5.5216

Max Act: 4.6447. Min Act: -0.0000

Data Index: 1286413 (The Pile)

Max Activating Token Index: 17

Text #6

Max Range: 5.5216. Min Range: -5.5216

Max Act: 4.5055. Min Act: -0.0000

Data Index: 1713642 (The Pile)

Max Activating Token Index: 72

Text #7

Max Range: 5.5216. Min Range: -5.5216

Max Act: 4.4707. Min Act: -0.0000

Data Index: 1419102 (The Pile)

Max Activating Token Index: 130

Text #8

Max Range: 5.5216. Min Range: -5.5216

Max Act: 4.0969. Min Act: -0.0000

Data Index: 703315 (The Pile)

Max Activating Token Index: 117

Text #9

Max Range: 5.5216. Min Range: -5.5216

Max Act: 4.0752. Min Act: -0.0000

Data Index: 315927 (The Pile)

Max Activating Token Index: 120

Text #10

Max Range: 5.5216. Min Range: -5.5216

Max Act: 4.0804. Min Act: -0.0000

Data Index: 436111 (The Pile)

Max Activating Token Index: 97

Text #11

Max Range: 5.5216. Min Range: -5.5216

Max Act: 4.0682. Min Act: -0.0000

Data Index: 845123 (The Pile)

Max Activating Token Index: 241

Text #12

Max Range: 5.5216. Min Range: -5.5216

Max Act: 4.0382. Min Act: -0.0000

Data Index: 1201565 (The Pile)

Max Activating Token Index: 644

Text #13

Max Range: 5.5216. Min Range: -5.5216

Max Act: 4.1517. Min Act: -0.0000

Data Index: 473249 (The Pile)

Max Activating Token Index: 130

Text #14

Max Range: 5.5216. Min Range: -5.5216

Max Act: 4.1269. Min Act: -0.0000

Data Index: 907680 (The Pile)

Max Activating Token Index: 89

Text #15

Max Range: 5.5216. Min Range: -5.5216

Max Act: 4.4664. Min Act: -0.0000

Data Index: 1989224 (The Pile)

Max Activating Token Index: 111

Text #16

Max Range: 5.5216. Min Range: -5.5216

Max Act: 3.9093. Min Act: -0.0000

Data Index: 1455662 (The Pile)

Max Activating Token Index: 285

Text #17

Max Range: 5.5216. Min Range: -5.5216

Max Act: 3.4124. Min Act: -0.0000

Data Index: 1824952 (The Pile)

Max Activating Token Index: 1020

Text #18

Max Range: 5.5216. Min Range: -5.5216

Max Act: 3.8505. Min Act: -0.0000

Data Index: 485218 (The Pile)

Max Activating Token Index: 85

Text #19

Max Range: 5.5216. Min Range: -5.5216

Max Act: 4.3552. Min Act: -0.0000

Data Index: 1202581 (The Pile)

Max Activating Token Index: 38