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

Dataset: The Pile

Neuron 1105 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.4028. Min Range: -7.4028

Max Act: 7.3846. Min Act: -0.0000

Data Index: 651551 (The Pile)

Max Activating Token Index: 538

Text #1

Max Range: 7.4028. Min Range: -7.4028

Max Act: 7.2739. Min Act: -0.0000

Data Index: 1419550 (The Pile)

Max Activating Token Index: 91

Text #2

Max Range: 7.4028. Min Range: -7.4028

Max Act: 6.8847. Min Act: -0.0000

Data Index: 1765363 (The Pile)

Max Activating Token Index: 264

Text #3

Max Range: 7.4028. Min Range: -7.4028

Max Act: 7.4028. Min Act: -0.0000

Data Index: 39228 (The Pile)

Max Activating Token Index: 71

Text #4

Max Range: 7.4028. Min Range: -7.4028

Max Act: 6.8543. Min Act: -0.0000

Data Index: 120496 (The Pile)

Max Activating Token Index: 200

Text #5

Max Range: 7.4028. Min Range: -7.4028

Max Act: 6.8782. Min Act: -0.0000

Data Index: 1417325 (The Pile)

Max Activating Token Index: 121

Text #6

Max Range: 7.4028. Min Range: -7.4028

Max Act: 6.8615. Min Act: -0.0000

Data Index: 1958856 (The Pile)

Max Activating Token Index: 134

Text #7

Max Range: 7.4028. Min Range: -7.4028

Max Act: 7.2066. Min Act: -0.0000

Data Index: 204191 (The Pile)

Max Activating Token Index: 198

Text #8

Max Range: 7.4028. Min Range: -7.4028

Max Act: 6.9405. Min Act: -0.0000

Data Index: 1005987 (The Pile)

Max Activating Token Index: 65

Text #9

Max Range: 7.4028. Min Range: -7.4028

Max Act: 6.9246. Min Act: -0.0000

Data Index: 1682167 (The Pile)

Max Activating Token Index: 109

Text #10

Max Range: 7.4028. Min Range: -7.4028

Max Act: 7.0009. Min Act: -0.0000

Data Index: 1640472 (The Pile)

Max Activating Token Index: 136

Text #11

Max Range: 7.4028. Min Range: -7.4028

Max Act: 6.8051. Min Act: -0.0000

Data Index: 1419388 (The Pile)

Max Activating Token Index: 148

Text #12

Max Range: 7.4028. Min Range: -7.4028

Max Act: 6.7964. Min Act: -0.0000

Data Index: 1674295 (The Pile)

Max Activating Token Index: 177

Text #13

Max Range: 7.4028. Min Range: -7.4028

Max Act: 7.1665. Min Act: -0.0000

Data Index: 30676 (The Pile)

Max Activating Token Index: 137

Text #14

Max Range: 7.4028. Min Range: -7.4028

Max Act: 6.3506. Min Act: -0.0000

Data Index: 746146 (The Pile)

Max Activating Token Index: 83

Text #15

Max Range: 7.4028. Min Range: -7.4028

Max Act: 6.5571. Min Act: -0.0000

Data Index: 1776299 (The Pile)

Max Activating Token Index: 231

Text #16

Max Range: 7.4028. Min Range: -7.4028

Max Act: 6.9829. Min Act: -0.0000

Data Index: 349316 (The Pile)

Max Activating Token Index: 149

Text #17

Max Range: 7.4028. Min Range: -7.4028

Max Act: 6.9022. Min Act: -0.0000

Data Index: 817869 (The Pile)

Max Activating Token Index: 130

Text #18

Max Range: 7.4028. Min Range: -7.4028

Max Act: 6.6705. Min Act: -0.0000

Data Index: 968727 (The Pile)

Max Activating Token Index: 51

Text #19

Max Range: 7.4028. Min Range: -7.4028

Max Act: 6.2291. Min Act: -0.0000

Data Index: 1059194 (The Pile)

Max Activating Token Index: 171