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

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

Neuron 347 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.9567. Min Act: -0.0001

Data Index: 1041790 (C4 (Web Text))

Max Activating Token Index: 539

Text #1

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.7670. Min Act: -0.0001

Data Index: 1006774 (C4 (Web Text))

Max Activating Token Index: 207

Text #2

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.8694. Min Act: -0.0001

Data Index: 739074 (C4 (Web Text))

Max Activating Token Index: 140

Text #3

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.7108. Min Act: -0.0001

Data Index: 233176 (C4 (Web Text))

Max Activating Token Index: 140

Text #4

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.6977. Min Act: -0.0001

Data Index: 513694 (C4 (Web Text))

Max Activating Token Index: 566

Text #5

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.6534. Min Act: -0.0001

Data Index: 219418 (C4 (Web Text))

Max Activating Token Index: 895

Text #6

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.7091. Min Act: -0.0001

Data Index: 1284204 (C4 (Web Text))

Max Activating Token Index: 909

Text #7

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.6169. Min Act: -0.0001

Data Index: 494730 (C4 (Web Text))

Max Activating Token Index: 766

Text #8

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.6479. Min Act: -0.0001

Data Index: 1413396 (Python Code)

Max Activating Token Index: 100

Text #9

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.6432. Min Act: -0.0001

Data Index: 565818 (C4 (Web Text))

Max Activating Token Index: 972

Text #10

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.6296. Min Act: -0.0001

Data Index: 1462871 (Python Code)

Max Activating Token Index: 237

Text #11

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.6400. Min Act: -0.0001

Data Index: 567694 (C4 (Web Text))

Max Activating Token Index: 811

Text #12

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.6040. Min Act: -0.0001

Data Index: 1179160 (C4 (Web Text))

Max Activating Token Index: 830

Text #13

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.5898. Min Act: -0.0001

Data Index: 46924 (C4 (Web Text))

Max Activating Token Index: 769

Text #14

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.6336. Min Act: -0.0001

Data Index: 110713 (C4 (Web Text))

Max Activating Token Index: 950

Text #15

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.6270. Min Act: -0.0001

Data Index: 832008 (C4 (Web Text))

Max Activating Token Index: 948

Text #16

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.6285. Min Act: -0.0001

Data Index: 2397 (C4 (Web Text))

Max Activating Token Index: 574

Text #17

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.5877. Min Act: -0.0001

Data Index: 400885 (C4 (Web Text))

Max Activating Token Index: 501

Text #18

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.6214. Min Act: -0.0001

Data Index: 557128 (C4 (Web Text))

Max Activating Token Index: 876

Text #19

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.6004. Min Act: -0.0001

Data Index: 995442 (C4 (Web Text))

Max Activating Token Index: 735