Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1504 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.7256. Min Range: -2.7256

Max Act: 2.7256. Min Act: -0.0000

Data Index: 1271902 (C4 (Web Text))

Max Activating Token Index: 1013

Text #1

Max Range: 2.7256. Min Range: -2.7256

Max Act: 2.5342. Min Act: -0.0000

Data Index: 1191121 (C4 (Web Text))

Max Activating Token Index: 965

Text #2

Max Range: 2.7256. Min Range: -2.7256

Max Act: 2.3284. Min Act: 0.0001

Data Index: 376320 (C4 (Web Text))

Max Activating Token Index: 249

Text #3

Max Range: 2.7256. Min Range: -2.7256

Max Act: 2.1984. Min Act: -0.0000

Data Index: 1138521 (C4 (Web Text))

Max Activating Token Index: 363

Text #4

Max Range: 2.7256. Min Range: -2.7256

Max Act: 2.1791. Min Act: -0.0000

Data Index: 1172541 (C4 (Web Text))

Max Activating Token Index: 1008

Text #5

Max Range: 2.7256. Min Range: -2.7256

Max Act: 2.2219. Min Act: -0.0000

Data Index: 437616 (C4 (Web Text))

Max Activating Token Index: 408

Text #6

Max Range: 2.7256. Min Range: -2.7256

Max Act: 2.2223. Min Act: 0.0000

Data Index: 948984 (C4 (Web Text))

Max Activating Token Index: 53

Text #7

Max Range: 2.7256. Min Range: -2.7256

Max Act: 2.1025. Min Act: -0.0000

Data Index: 214039 (C4 (Web Text))

Max Activating Token Index: 227

Text #8

Max Range: 2.7256. Min Range: -2.7256

Max Act: 2.0861. Min Act: 0.0000

Data Index: 341574 (C4 (Web Text))

Max Activating Token Index: 408

Text #9

Max Range: 2.7256. Min Range: -2.7256

Max Act: 2.1893. Min Act: -0.0000

Data Index: 1042176 (C4 (Web Text))

Max Activating Token Index: 268

Text #10

Max Range: 2.7256. Min Range: -2.7256

Max Act: 2.1783. Min Act: -0.0000

Data Index: 115410 (C4 (Web Text))

Max Activating Token Index: 161

Text #11

Max Range: 2.7256. Min Range: -2.7256

Max Act: 2.0953. Min Act: -0.0000

Data Index: 1094458 (C4 (Web Text))

Max Activating Token Index: 500

Text #12

Max Range: 2.7256. Min Range: -2.7256

Max Act: 2.0914. Min Act: 0.0000

Data Index: 1328848 (C4 (Web Text))

Max Activating Token Index: 838

Text #13

Max Range: 2.7256. Min Range: -2.7256

Max Act: 1.9184. Min Act: -0.0000

Data Index: 560286 (C4 (Web Text))

Max Activating Token Index: 493

Text #14

Max Range: 2.7256. Min Range: -2.7256

Max Act: 2.0093. Min Act: -0.0000

Data Index: 811369 (C4 (Web Text))

Max Activating Token Index: 459

Text #15

Max Range: 2.7256. Min Range: -2.7256

Max Act: 1.9853. Min Act: -0.0000

Data Index: 1172917 (C4 (Web Text))

Max Activating Token Index: 380

Text #16

Max Range: 2.7256. Min Range: -2.7256

Max Act: 1.8773. Min Act: -0.0000

Data Index: 665555 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 2.7256. Min Range: -2.7256

Max Act: 1.9745. Min Act: -0.0000

Data Index: 599096 (C4 (Web Text))

Max Activating Token Index: 36

Text #18

Max Range: 2.7256. Min Range: -2.7256

Max Act: 1.9534. Min Act: -0.0000

Data Index: 833963 (C4 (Web Text))

Max Activating Token Index: 528

Text #19

Max Range: 2.7256. Min Range: -2.7256

Max Act: 1.9523. Min Act: 0.0001

Data Index: 957202 (C4 (Web Text))

Max Activating Token Index: 430