Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2803 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1978. Min Act: -0.0001

Data Index: 582528 (C4 (Web Text))

Max Activating Token Index: 667

Text #1

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.2127. Min Act: -0.0001

Data Index: 566315 (C4 (Web Text))

Max Activating Token Index: 119

Text #2

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.2093. Min Act: -0.0001

Data Index: 1203610 (C4 (Web Text))

Max Activating Token Index: 61

Text #3

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.2005. Min Act: -0.0001

Data Index: 179612 (C4 (Web Text))

Max Activating Token Index: 439

Text #4

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1965. Min Act: -0.0001

Data Index: 659382 (C4 (Web Text))

Max Activating Token Index: 344

Text #5

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.2006. Min Act: -0.0001

Data Index: 519183 (C4 (Web Text))

Max Activating Token Index: 963

Text #6

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1677. Min Act: -0.0001

Data Index: 957376 (C4 (Web Text))

Max Activating Token Index: 274

Text #7

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1975. Min Act: -0.0001

Data Index: 1115133 (C4 (Web Text))

Max Activating Token Index: 209

Text #8

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1972. Min Act: -0.0001

Data Index: 1312785 (C4 (Web Text))

Max Activating Token Index: 113

Text #9

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1982. Min Act: -0.0001

Data Index: 1317123 (C4 (Web Text))

Max Activating Token Index: 926

Text #10

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1801. Min Act: -0.0001

Data Index: 730457 (C4 (Web Text))

Max Activating Token Index: 77

Text #11

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1848. Min Act: -0.0001

Data Index: 158901 (C4 (Web Text))

Max Activating Token Index: 113

Text #12

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1838. Min Act: -0.0001

Data Index: 1291648 (C4 (Web Text))

Max Activating Token Index: 605

Text #13

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1967. Min Act: -0.0001

Data Index: 1286050 (C4 (Web Text))

Max Activating Token Index: 552

Text #14

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1821. Min Act: -0.0001

Data Index: 811911 (C4 (Web Text))

Max Activating Token Index: 252

Text #15

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.2075. Min Act: -0.0001

Data Index: 27347 (C4 (Web Text))

Max Activating Token Index: 567

Text #16

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1637. Min Act: -0.0001

Data Index: 579048 (C4 (Web Text))

Max Activating Token Index: 294

Text #17

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1818. Min Act: -0.0001

Data Index: 546252 (C4 (Web Text))

Max Activating Token Index: 145

Text #18

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1866. Min Act: -0.0001

Data Index: 923635 (C4 (Web Text))

Max Activating Token Index: 782

Text #19

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1821. Min Act: -0.0001

Data Index: 85832 (C4 (Web Text))

Max Activating Token Index: 44