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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2738 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.1484. Min Range: -8.1484

Max Act: 8.1484. Min Act: -0.0000

Data Index: 946918 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 8.1484. Min Range: -8.1484

Max Act: 7.5153. Min Act: -0.0000

Data Index: 1278839 (C4 (Web Text))

Max Activating Token Index: 823

Text #2

Max Range: 8.1484. Min Range: -8.1484

Max Act: 7.0638. Min Act: -0.0000

Data Index: 500800 (C4 (Web Text))

Max Activating Token Index: 77

Text #3

Max Range: 8.1484. Min Range: -8.1484

Max Act: 6.5062. Min Act: -0.0000

Data Index: 734565 (C4 (Web Text))

Max Activating Token Index: 128

Text #4

Max Range: 8.1484. Min Range: -8.1484

Max Act: 5.9278. Min Act: -0.0000

Data Index: 637946 (C4 (Web Text))

Max Activating Token Index: 749

Text #5

Max Range: 8.1484. Min Range: -8.1484

Max Act: 6.2844. Min Act: -0.0000

Data Index: 1207670 (C4 (Web Text))

Max Activating Token Index: 1010

Text #6

Max Range: 8.1484. Min Range: -8.1484

Max Act: 6.1975. Min Act: -0.0000

Data Index: 1313967 (C4 (Web Text))

Max Activating Token Index: 125

Text #7

Max Range: 8.1484. Min Range: -8.1484

Max Act: 6.2197. Min Act: -0.0000

Data Index: 1215472 (C4 (Web Text))

Max Activating Token Index: 758

Text #8

Max Range: 8.1484. Min Range: -8.1484

Max Act: 6.3327. Min Act: -0.0000

Data Index: 471802 (C4 (Web Text))

Max Activating Token Index: 353

Text #9

Max Range: 8.1484. Min Range: -8.1484

Max Act: 6.3230. Min Act: -0.0000

Data Index: 525545 (C4 (Web Text))

Max Activating Token Index: 860

Text #10

Max Range: 8.1484. Min Range: -8.1484

Max Act: 5.9538. Min Act: -0.0000

Data Index: 155045 (C4 (Web Text))

Max Activating Token Index: 959

Text #11

Max Range: 8.1484. Min Range: -8.1484

Max Act: 6.2443. Min Act: -0.0000

Data Index: 1276786 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 8.1484. Min Range: -8.1484

Max Act: 6.0558. Min Act: -0.0000

Data Index: 1081569 (C4 (Web Text))

Max Activating Token Index: 664

Text #13

Max Range: 8.1484. Min Range: -8.1484

Max Act: 5.7789. Min Act: -0.0000

Data Index: 721380 (C4 (Web Text))

Max Activating Token Index: 678

Text #14

Max Range: 8.1484. Min Range: -8.1484

Max Act: 5.7657. Min Act: -0.0000

Data Index: 565420 (C4 (Web Text))

Max Activating Token Index: 284

Text #15

Max Range: 8.1484. Min Range: -8.1484

Max Act: 6.2459. Min Act: -0.0000

Data Index: 772339 (C4 (Web Text))

Max Activating Token Index: 277

Text #16

Max Range: 8.1484. Min Range: -8.1484

Max Act: 6.3990. Min Act: -0.0000

Data Index: 1073953 (C4 (Web Text))

Max Activating Token Index: 807

Text #17

Max Range: 8.1484. Min Range: -8.1484

Max Act: 6.0489. Min Act: -0.0001

Data Index: 947274 (C4 (Web Text))

Max Activating Token Index: 913

Text #18

Max Range: 8.1484. Min Range: -8.1484

Max Act: 5.6206. Min Act: -0.0000

Data Index: 198525 (C4 (Web Text))

Max Activating Token Index: 232

Text #19

Max Range: 8.1484. Min Range: -8.1484

Max Act: 5.7201. Min Act: -0.0000

Data Index: 869202 (C4 (Web Text))

Max Activating Token Index: 521