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

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

Neuron 3329 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: 0.9049. Min Range: -0.9049

Max Act: 0.9049. Min Act: -0.0001

Data Index: 1409635 (Python Code)

Max Activating Token Index: 140

Text #1

Max Range: 0.9049. Min Range: -0.9049

Max Act: 0.8845. Min Act: -0.0001

Data Index: 438889 (C4 (Web Text))

Max Activating Token Index: 937

Text #2

Max Range: 0.9049. Min Range: -0.9049

Max Act: 0.7189. Min Act: -0.0001

Data Index: 586925 (C4 (Web Text))

Max Activating Token Index: 233

Text #3

Max Range: 0.9049. Min Range: -0.9049

Max Act: 0.7483. Min Act: -0.0001

Data Index: 413743 (C4 (Web Text))

Max Activating Token Index: 824

Text #4

Max Range: 0.9049. Min Range: -0.9049

Max Act: 0.7548. Min Act: -0.0001

Data Index: 1418637 (Python Code)

Max Activating Token Index: 176

Text #5

Max Range: 0.9049. Min Range: -0.9049

Max Act: 0.7062. Min Act: -0.0001

Data Index: 1500293 (Python Code)

Max Activating Token Index: 767

Text #6

Max Range: 0.9049. Min Range: -0.9049

Max Act: 0.7569. Min Act: -0.0001

Data Index: 1236388 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.9049. Min Range: -0.9049

Max Act: 0.7349. Min Act: -0.0001

Data Index: 886164 (C4 (Web Text))

Max Activating Token Index: 513

Text #8

Max Range: 0.9049. Min Range: -0.9049

Max Act: 0.6680. Min Act: -0.0001

Data Index: 1621871 (Python Code)

Max Activating Token Index: 487

Text #9

Max Range: 0.9049. Min Range: -0.9049

Max Act: 0.7371. Min Act: -0.0001

Data Index: 1119455 (C4 (Web Text))

Max Activating Token Index: 484

Text #10

Max Range: 0.9049. Min Range: -0.9049

Max Act: 0.6328. Min Act: -0.0001

Data Index: 388330 (C4 (Web Text))

Max Activating Token Index: 698

Text #11

Max Range: 0.9049. Min Range: -0.9049

Max Act: 0.6758. Min Act: -0.0001

Data Index: 1241794 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 0.9049. Min Range: -0.9049

Max Act: 0.6985. Min Act: -0.0001

Data Index: 1605611 (Python Code)

Max Activating Token Index: 990

Text #13

Max Range: 0.9049. Min Range: -0.9049

Max Act: 0.7211. Min Act: -0.0001

Data Index: 387942 (C4 (Web Text))

Max Activating Token Index: 227

Text #14

Max Range: 0.9049. Min Range: -0.9049

Max Act: 0.7182. Min Act: -0.0001

Data Index: 25719 (C4 (Web Text))

Max Activating Token Index: 797

Text #15

Max Range: 0.9049. Min Range: -0.9049

Max Act: 0.6941. Min Act: -0.0001

Data Index: 1444755 (Python Code)

Max Activating Token Index: 411

Text #16

Max Range: 0.9049. Min Range: -0.9049

Max Act: 0.6624. Min Act: -0.0001

Data Index: 1303968 (C4 (Web Text))

Max Activating Token Index: 331

Text #17

Max Range: 0.9049. Min Range: -0.9049

Max Act: 0.6903. Min Act: -0.0001

Data Index: 1515783 (Python Code)

Max Activating Token Index: 927

Text #18

Max Range: 0.9049. Min Range: -0.9049

Max Act: 0.7039. Min Act: -0.0001

Data Index: 547396 (C4 (Web Text))

Max Activating Token Index: 158

Text #19

Max Range: 0.9049. Min Range: -0.9049

Max Act: 0.6822. Min Act: -0.0001

Data Index: 584066 (C4 (Web Text))

Max Activating Token Index: 29