Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3818 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.3947. Min Act: -0.0002

Data Index: 29632 (C4 (Web Text))

Max Activating Token Index: 595

Text #1

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.3480. Min Act: -0.0002

Data Index: 486844 (C4 (Web Text))

Max Activating Token Index: 899

Text #2

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.3994. Min Act: -0.0002

Data Index: 1138114 (C4 (Web Text))

Max Activating Token Index: 131

Text #3

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.4024. Min Act: -0.0002

Data Index: 800575 (C4 (Web Text))

Max Activating Token Index: 1008

Text #4

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.3481. Min Act: -0.0002

Data Index: 1079674 (C4 (Web Text))

Max Activating Token Index: 5

Text #5

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.3618. Min Act: -0.0002

Data Index: 678262 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.3594. Min Act: -0.0002

Data Index: 1262211 (C4 (Web Text))

Max Activating Token Index: 913

Text #7

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.3646. Min Act: -0.0002

Data Index: 1073417 (C4 (Web Text))

Max Activating Token Index: 917

Text #8

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.3032. Min Act: -0.0002

Data Index: 1324077 (C4 (Web Text))

Max Activating Token Index: 677

Text #9

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.3348. Min Act: -0.0002

Data Index: 1089192 (C4 (Web Text))

Max Activating Token Index: 189

Text #10

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.3356. Min Act: -0.0002

Data Index: 882184 (C4 (Web Text))

Max Activating Token Index: 643

Text #11

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.2974. Min Act: -0.0002

Data Index: 1121921 (C4 (Web Text))

Max Activating Token Index: 223

Text #12

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.3396. Min Act: -0.0002

Data Index: 1073974 (C4 (Web Text))

Max Activating Token Index: 419

Text #13

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.3051. Min Act: -0.0002

Data Index: 661588 (C4 (Web Text))

Max Activating Token Index: 735

Text #14

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.3357. Min Act: -0.0002

Data Index: 1016414 (C4 (Web Text))

Max Activating Token Index: 929

Text #15

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.3338. Min Act: -0.0002

Data Index: 439081 (C4 (Web Text))

Max Activating Token Index: 434

Text #16

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.3162. Min Act: -0.0002

Data Index: 1262662 (C4 (Web Text))

Max Activating Token Index: 836

Text #17

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.3262. Min Act: -0.0002

Data Index: 626575 (C4 (Web Text))

Max Activating Token Index: 432

Text #18

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.3151. Min Act: -0.0002

Data Index: 1130248 (C4 (Web Text))

Max Activating Token Index: 674

Text #19

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.3030. Min Act: -0.0002

Data Index: 669317 (C4 (Web Text))

Max Activating Token Index: 661