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

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

Neuron 458 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: 0.1269. Min Range: -0.1269

Max Act: 0.1269. Min Act: -0.0001

Data Index: 791279 (C4 (Web Text))

Max Activating Token Index: 44

Text #1

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.1252. Min Act: -0.0001

Data Index: 883598 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.1094. Min Act: -0.0001

Data Index: 613559 (C4 (Web Text))

Max Activating Token Index: 817

Text #3

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.1241. Min Act: -0.0001

Data Index: 443990 (C4 (Web Text))

Max Activating Token Index: 910

Text #4

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.1195. Min Act: -0.0001

Data Index: 1017498 (C4 (Web Text))

Max Activating Token Index: 229

Text #5

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.1152. Min Act: -0.0001

Data Index: 953718 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.1078. Min Act: -0.0001

Data Index: 211232 (C4 (Web Text))

Max Activating Token Index: 345

Text #7

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.1094. Min Act: -0.0001

Data Index: 678370 (C4 (Web Text))

Max Activating Token Index: 488

Text #8

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.1087. Min Act: -0.0001

Data Index: 190346 (C4 (Web Text))

Max Activating Token Index: 49

Text #9

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.1082. Min Act: -0.0001

Data Index: 976957 (C4 (Web Text))

Max Activating Token Index: 80

Text #10

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.1094. Min Act: -0.0001

Data Index: 361122 (C4 (Web Text))

Max Activating Token Index: 158

Text #11

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.1116. Min Act: -0.0001

Data Index: 709154 (C4 (Web Text))

Max Activating Token Index: 341

Text #12

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.1083. Min Act: -0.0001

Data Index: 1293500 (C4 (Web Text))

Max Activating Token Index: 367

Text #13

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.0970. Min Act: -0.0001

Data Index: 705986 (C4 (Web Text))

Max Activating Token Index: 1006

Text #14

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.1008. Min Act: -0.0001

Data Index: 115567 (C4 (Web Text))

Max Activating Token Index: 163

Text #15

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.1034. Min Act: -0.0001

Data Index: 717165 (C4 (Web Text))

Max Activating Token Index: 97

Text #16

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.1077. Min Act: -0.0001

Data Index: 1165140 (C4 (Web Text))

Max Activating Token Index: 198

Text #17

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.0993. Min Act: -0.0001

Data Index: 834287 (C4 (Web Text))

Max Activating Token Index: 690

Text #18

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.0996. Min Act: -0.0001

Data Index: 605630 (C4 (Web Text))

Max Activating Token Index: 561

Text #19

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.0979. Min Act: -0.0001

Data Index: 285477 (C4 (Web Text))

Max Activating Token Index: 400