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

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

Neuron 1841 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3214. Min Range: -1.3214

Max Act: 1.3214. Min Act: -0.0001

Data Index: 129296 (C4 (Web Text))

Max Activating Token Index: 508

Text #1

Max Range: 1.3214. Min Range: -1.3214

Max Act: 1.1410. Min Act: -0.0001

Data Index: 624249 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 1.3214. Min Range: -1.3214

Max Act: 1.1037. Min Act: -0.0001

Data Index: 503581 (C4 (Web Text))

Max Activating Token Index: 493

Text #3

Max Range: 1.3214. Min Range: -1.3214

Max Act: 1.0292. Min Act: -0.0001

Data Index: 1014842 (C4 (Web Text))

Max Activating Token Index: 167

Text #4

Max Range: 1.3214. Min Range: -1.3214

Max Act: 0.9312. Min Act: -0.0001

Data Index: 272439 (C4 (Web Text))

Max Activating Token Index: 477

Text #5

Max Range: 1.3214. Min Range: -1.3214

Max Act: 0.9537. Min Act: -0.0001

Data Index: 84241 (C4 (Web Text))

Max Activating Token Index: 829

Text #6

Max Range: 1.3214. Min Range: -1.3214

Max Act: 0.9023. Min Act: -0.0001

Data Index: 1183929 (C4 (Web Text))

Max Activating Token Index: 93

Text #7

Max Range: 1.3214. Min Range: -1.3214

Max Act: 0.8469. Min Act: -0.0001

Data Index: 923778 (C4 (Web Text))

Max Activating Token Index: 616

Text #8

Max Range: 1.3214. Min Range: -1.3214

Max Act: 0.9354. Min Act: -0.0001

Data Index: 962262 (C4 (Web Text))

Max Activating Token Index: 129

Text #9

Max Range: 1.3214. Min Range: -1.3214

Max Act: 0.9044. Min Act: -0.0001

Data Index: 634146 (C4 (Web Text))

Max Activating Token Index: 513

Text #10

Max Range: 1.3214. Min Range: -1.3214

Max Act: 0.9567. Min Act: -0.0001

Data Index: 119174 (C4 (Web Text))

Max Activating Token Index: 476

Text #11

Max Range: 1.3214. Min Range: -1.3214

Max Act: 0.8785. Min Act: -0.0001

Data Index: 1292976 (C4 (Web Text))

Max Activating Token Index: 300

Text #12

Max Range: 1.3214. Min Range: -1.3214

Max Act: 0.8664. Min Act: -0.0001

Data Index: 307837 (C4 (Web Text))

Max Activating Token Index: 126

Text #13

Max Range: 1.3214. Min Range: -1.3214

Max Act: 0.9039. Min Act: -0.0001

Data Index: 90159 (C4 (Web Text))

Max Activating Token Index: 253

Text #14

Max Range: 1.3214. Min Range: -1.3214

Max Act: 0.8781. Min Act: -0.0001

Data Index: 101783 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 1.3214. Min Range: -1.3214

Max Act: 0.7891. Min Act: -0.0001

Data Index: 196336 (C4 (Web Text))

Max Activating Token Index: 870

Text #16

Max Range: 1.3214. Min Range: -1.3214

Max Act: 0.8978. Min Act: -0.0001

Data Index: 615994 (C4 (Web Text))

Max Activating Token Index: 83

Text #17

Max Range: 1.3214. Min Range: -1.3214

Max Act: 0.8826. Min Act: -0.0001

Data Index: 847059 (C4 (Web Text))

Max Activating Token Index: 119

Text #18

Max Range: 1.3214. Min Range: -1.3214

Max Act: 0.7938. Min Act: -0.0001

Data Index: 788679 (C4 (Web Text))

Max Activating Token Index: 814

Text #19

Max Range: 1.3214. Min Range: -1.3214

Max Act: 0.8446. Min Act: -0.0001

Data Index: 48386 (C4 (Web Text))

Max Activating Token Index: 543