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

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

Neuron 2010 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3049. Min Range: -1.3049

Max Act: 1.3049. Min Act: -0.0001

Data Index: 987325 (C4 (Web Text))

Max Activating Token Index: 629

Text #1

Max Range: 1.3049. Min Range: -1.3049

Max Act: 1.1241. Min Act: -0.0001

Data Index: 937834 (C4 (Web Text))

Max Activating Token Index: 903

Text #2

Max Range: 1.3049. Min Range: -1.3049

Max Act: 1.1090. Min Act: -0.0001

Data Index: 1123172 (C4 (Web Text))

Max Activating Token Index: 321

Text #3

Max Range: 1.3049. Min Range: -1.3049

Max Act: 1.1083. Min Act: -0.0001

Data Index: 1030582 (C4 (Web Text))

Max Activating Token Index: 492

Text #4

Max Range: 1.3049. Min Range: -1.3049

Max Act: 1.0755. Min Act: -0.0001

Data Index: 13328 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 1.3049. Min Range: -1.3049

Max Act: 1.0628. Min Act: -0.0001

Data Index: 964526 (C4 (Web Text))

Max Activating Token Index: 211

Text #6

Max Range: 1.3049. Min Range: -1.3049

Max Act: 1.0213. Min Act: -0.0001

Data Index: 625251 (C4 (Web Text))

Max Activating Token Index: 483

Text #7

Max Range: 1.3049. Min Range: -1.3049

Max Act: 1.0749. Min Act: -0.0001

Data Index: 1004345 (C4 (Web Text))

Max Activating Token Index: 258

Text #8

Max Range: 1.3049. Min Range: -1.3049

Max Act: 1.0161. Min Act: -0.0001

Data Index: 1002318 (C4 (Web Text))

Max Activating Token Index: 409

Text #9

Max Range: 1.3049. Min Range: -1.3049

Max Act: 1.0317. Min Act: -0.0001

Data Index: 700621 (C4 (Web Text))

Max Activating Token Index: 435

Text #10

Max Range: 1.3049. Min Range: -1.3049

Max Act: 0.9998. Min Act: -0.0001

Data Index: 885369 (C4 (Web Text))

Max Activating Token Index: 1022

Text #11

Max Range: 1.3049. Min Range: -1.3049

Max Act: 0.9894. Min Act: -0.0001

Data Index: 1208121 (C4 (Web Text))

Max Activating Token Index: 468

Text #12

Max Range: 1.3049. Min Range: -1.3049

Max Act: 0.9867. Min Act: -0.0001

Data Index: 772549 (C4 (Web Text))

Max Activating Token Index: 127

Text #13

Max Range: 1.3049. Min Range: -1.3049

Max Act: 0.9577. Min Act: -0.0001

Data Index: 998150 (C4 (Web Text))

Max Activating Token Index: 243

Text #14

Max Range: 1.3049. Min Range: -1.3049

Max Act: 1.0433. Min Act: -0.0001

Data Index: 1065396 (C4 (Web Text))

Max Activating Token Index: 91

Text #15

Max Range: 1.3049. Min Range: -1.3049

Max Act: 1.0072. Min Act: -0.0001

Data Index: 461654 (C4 (Web Text))

Max Activating Token Index: 164

Text #16

Max Range: 1.3049. Min Range: -1.3049

Max Act: 0.9704. Min Act: -0.0001

Data Index: 1190264 (C4 (Web Text))

Max Activating Token Index: 699

Text #17

Max Range: 1.3049. Min Range: -1.3049

Max Act: 0.9387. Min Act: -0.0001

Data Index: 372948 (C4 (Web Text))

Max Activating Token Index: 341

Text #18

Max Range: 1.3049. Min Range: -1.3049

Max Act: 0.9969. Min Act: -0.0001

Data Index: 394325 (C4 (Web Text))

Max Activating Token Index: 378

Text #19

Max Range: 1.3049. Min Range: -1.3049

Max Act: 0.9653. Min Act: -0.0001

Data Index: 869773 (C4 (Web Text))

Max Activating Token Index: 470