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

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

Neuron 486 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: 0.3635. Min Range: -0.3635

Max Act: 0.3635. Min Act: -0.0001

Data Index: 662295 (C4 (Web Text))

Max Activating Token Index: 934

Text #1

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.3281. Min Act: -0.0001

Data Index: 170152 (C4 (Web Text))

Max Activating Token Index: 61

Text #2

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.3132. Min Act: -0.0001

Data Index: 1067574 (C4 (Web Text))

Max Activating Token Index: 747

Text #3

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.2999. Min Act: -0.0001

Data Index: 655762 (C4 (Web Text))

Max Activating Token Index: 209

Text #4

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.3111. Min Act: -0.0001

Data Index: 889107 (C4 (Web Text))

Max Activating Token Index: 378

Text #5

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.3322. Min Act: -0.0001

Data Index: 467560 (C4 (Web Text))

Max Activating Token Index: 321

Text #6

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.3296. Min Act: -0.0001

Data Index: 966346 (C4 (Web Text))

Max Activating Token Index: 580

Text #7

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.3191. Min Act: -0.0001

Data Index: 243416 (C4 (Web Text))

Max Activating Token Index: 109

Text #8

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.3091. Min Act: -0.0001

Data Index: 1162014 (C4 (Web Text))

Max Activating Token Index: 166

Text #9

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.3070. Min Act: -0.0001

Data Index: 403856 (C4 (Web Text))

Max Activating Token Index: 203

Text #10

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.3088. Min Act: -0.0001

Data Index: 1093855 (C4 (Web Text))

Max Activating Token Index: 210

Text #11

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.3247. Min Act: -0.0001

Data Index: 1074675 (C4 (Web Text))

Max Activating Token Index: 182

Text #12

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.2960. Min Act: -0.0001

Data Index: 736570 (C4 (Web Text))

Max Activating Token Index: 181

Text #13

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.3122. Min Act: -0.0001

Data Index: 164265 (C4 (Web Text))

Max Activating Token Index: 255

Text #14

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.3125. Min Act: -0.0001

Data Index: 668412 (C4 (Web Text))

Max Activating Token Index: 376

Text #15

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.3110. Min Act: -0.0001

Data Index: 809412 (C4 (Web Text))

Max Activating Token Index: 386

Text #16

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.2892. Min Act: -0.0001

Data Index: 2063 (C4 (Web Text))

Max Activating Token Index: 494

Text #17

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.3095. Min Act: -0.0001

Data Index: 827868 (C4 (Web Text))

Max Activating Token Index: 304

Text #18

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.2992. Min Act: -0.0001

Data Index: 688849 (C4 (Web Text))

Max Activating Token Index: 78

Text #19

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.2982. Min Act: -0.0001

Data Index: 83481 (C4 (Web Text))

Max Activating Token Index: 589