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

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

Neuron 254 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.5150. Min Act: -0.0002

Data Index: 669115 (C4 (Web Text))

Max Activating Token Index: 277

Text #1

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.4949. Min Act: -0.0003

Data Index: 1325025 (C4 (Web Text))

Max Activating Token Index: 500

Text #2

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.4355. Min Act: -0.0003

Data Index: 250736 (C4 (Web Text))

Max Activating Token Index: 639

Text #3

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.4390. Min Act: -0.0003

Data Index: 150553 (C4 (Web Text))

Max Activating Token Index: 843

Text #4

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.4362. Min Act: -0.0003

Data Index: 699757 (C4 (Web Text))

Max Activating Token Index: 944

Text #5

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.4342. Min Act: -0.0002

Data Index: 746579 (C4 (Web Text))

Max Activating Token Index: 658

Text #6

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.4186. Min Act: -0.0002

Data Index: 476328 (C4 (Web Text))

Max Activating Token Index: 836

Text #7

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.4122. Min Act: -0.0003

Data Index: 1252907 (C4 (Web Text))

Max Activating Token Index: 170

Text #8

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.4055. Min Act: -0.0003

Data Index: 716758 (C4 (Web Text))

Max Activating Token Index: 847

Text #9

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.4039. Min Act: -0.0003

Data Index: 2476 (C4 (Web Text))

Max Activating Token Index: 230

Text #10

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.4006. Min Act: -0.0002

Data Index: 737261 (C4 (Web Text))

Max Activating Token Index: 969

Text #11

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.3998. Min Act: -0.0002

Data Index: 662302 (C4 (Web Text))

Max Activating Token Index: 326

Text #12

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.3867. Min Act: -0.0003

Data Index: 1340051 (C4 (Web Text))

Max Activating Token Index: 643

Text #13

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.3982. Min Act: -0.0003

Data Index: 176388 (C4 (Web Text))

Max Activating Token Index: 209

Text #14

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.3986. Min Act: -0.0003

Data Index: 338172 (C4 (Web Text))

Max Activating Token Index: 657

Text #15

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.3960. Min Act: -0.0003

Data Index: 1022127 (C4 (Web Text))

Max Activating Token Index: 80

Text #16

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.3923. Min Act: -0.0003

Data Index: 1151652 (C4 (Web Text))

Max Activating Token Index: 704

Text #17

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.3911. Min Act: -0.0003

Data Index: 896206 (C4 (Web Text))

Max Activating Token Index: 393

Text #18

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.3916. Min Act: -0.0003

Data Index: 684888 (C4 (Web Text))

Max Activating Token Index: 726

Text #19

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.3882. Min Act: -0.0003

Data Index: 528977 (C4 (Web Text))

Max Activating Token Index: 513