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

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

Neuron 1 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2920. Min Range: -0.2920

Max Act: 0.2920. Min Act: -0.0001

Data Index: 1450084 (Python Code)

Max Activating Token Index: 36

Text #1

Max Range: 0.2920. Min Range: -0.2920

Max Act: 0.2869. Min Act: -0.0001

Data Index: 1094215 (C4 (Web Text))

Max Activating Token Index: 436

Text #2

Max Range: 0.2920. Min Range: -0.2920

Max Act: 0.2676. Min Act: -0.0001

Data Index: 928953 (C4 (Web Text))

Max Activating Token Index: 807

Text #3

Max Range: 0.2920. Min Range: -0.2920

Max Act: 0.2448. Min Act: -0.0001

Data Index: 1580520 (Python Code)

Max Activating Token Index: 492

Text #4

Max Range: 0.2920. Min Range: -0.2920

Max Act: 0.2341. Min Act: -0.0001

Data Index: 697247 (C4 (Web Text))

Max Activating Token Index: 191

Text #5

Max Range: 0.2920. Min Range: -0.2920

Max Act: 0.2237. Min Act: -0.0001

Data Index: 656374 (C4 (Web Text))

Max Activating Token Index: 398

Text #6

Max Range: 0.2920. Min Range: -0.2920

Max Act: 0.2226. Min Act: -0.0001

Data Index: 964327 (C4 (Web Text))

Max Activating Token Index: 219

Text #7

Max Range: 0.2920. Min Range: -0.2920

Max Act: 0.2139. Min Act: -0.0001

Data Index: 1440548 (Python Code)

Max Activating Token Index: 16

Text #8

Max Range: 0.2920. Min Range: -0.2920

Max Act: 0.2193. Min Act: -0.0001

Data Index: 1405435 (Python Code)

Max Activating Token Index: 711

Text #9

Max Range: 0.2920. Min Range: -0.2920

Max Act: 0.2142. Min Act: -0.0001

Data Index: 43736 (C4 (Web Text))

Max Activating Token Index: 866

Text #10

Max Range: 0.2920. Min Range: -0.2920

Max Act: 0.2059. Min Act: -0.0001

Data Index: 1424153 (Python Code)

Max Activating Token Index: 819

Text #11

Max Range: 0.2920. Min Range: -0.2920

Max Act: 0.2143. Min Act: -0.0001

Data Index: 1655427 (Python Code)

Max Activating Token Index: 777

Text #12

Max Range: 0.2920. Min Range: -0.2920

Max Act: 0.1976. Min Act: -0.0001

Data Index: 27786 (C4 (Web Text))

Max Activating Token Index: 856

Text #13

Max Range: 0.2920. Min Range: -0.2920

Max Act: 0.1879. Min Act: -0.0001

Data Index: 1552301 (Python Code)

Max Activating Token Index: 159

Text #14

Max Range: 0.2920. Min Range: -0.2920

Max Act: 0.2004. Min Act: -0.0001

Data Index: 1103712 (C4 (Web Text))

Max Activating Token Index: 639

Text #15

Max Range: 0.2920. Min Range: -0.2920

Max Act: 0.1938. Min Act: -0.0001

Data Index: 1375380 (Python Code)

Max Activating Token Index: 644

Text #16

Max Range: 0.2920. Min Range: -0.2920

Max Act: 0.2079. Min Act: -0.0001

Data Index: 875773 (C4 (Web Text))

Max Activating Token Index: 291

Text #17

Max Range: 0.2920. Min Range: -0.2920

Max Act: 0.2062. Min Act: -0.0001

Data Index: 668910 (C4 (Web Text))

Max Activating Token Index: 441

Text #18

Max Range: 0.2920. Min Range: -0.2920

Max Act: 0.2056. Min Act: -0.0001

Data Index: 1438772 (Python Code)

Max Activating Token Index: 157

Text #19

Max Range: 0.2920. Min Range: -0.2920

Max Act: 0.1903. Min Act: -0.0001

Data Index: 1497280 (Python Code)

Max Activating Token Index: 167