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

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

Neuron 3256 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0090. Min Act: -0.0003

Data Index: 1077567 (C4 (Web Text))

Max Activating Token Index: 946

Text #1

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0096. Min Act: -0.0003

Data Index: 193395 (C4 (Web Text))

Max Activating Token Index: 451

Text #2

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0093. Min Act: -0.0003

Data Index: 1255747 (C4 (Web Text))

Max Activating Token Index: 835

Text #3

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0090. Min Act: -0.0003

Data Index: 1167490 (C4 (Web Text))

Max Activating Token Index: 482

Text #4

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0086. Min Act: -0.0003

Data Index: 415008 (C4 (Web Text))

Max Activating Token Index: 974

Text #5

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0072. Min Act: -0.0003

Data Index: 892461 (C4 (Web Text))

Max Activating Token Index: 542

Text #6

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0067. Min Act: -0.0003

Data Index: 814678 (C4 (Web Text))

Max Activating Token Index: 174

Text #7

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0078. Min Act: -0.0003

Data Index: 184969 (C4 (Web Text))

Max Activating Token Index: 1002

Text #8

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0083. Min Act: -0.0003

Data Index: 589148 (C4 (Web Text))

Max Activating Token Index: 469

Text #9

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0069. Min Act: -0.0003

Data Index: 122444 (C4 (Web Text))

Max Activating Token Index: 293

Text #10

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0078. Min Act: -0.0003

Data Index: 401646 (C4 (Web Text))

Max Activating Token Index: 289

Text #11

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0072. Min Act: -0.0003

Data Index: 1244423 (C4 (Web Text))

Max Activating Token Index: 952

Text #12

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0077. Min Act: -0.0003

Data Index: 1282479 (C4 (Web Text))

Max Activating Token Index: 645

Text #13

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0078. Min Act: -0.0003

Data Index: 308701 (C4 (Web Text))

Max Activating Token Index: 435

Text #14

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0071. Min Act: -0.0003

Data Index: 118528 (C4 (Web Text))

Max Activating Token Index: 700

Text #15

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0069. Min Act: -0.0003

Data Index: 358146 (C4 (Web Text))

Max Activating Token Index: 1007

Text #16

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0072. Min Act: -0.0003

Data Index: 1133762 (C4 (Web Text))

Max Activating Token Index: 193

Text #17

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0063. Min Act: -0.0003

Data Index: 577999 (C4 (Web Text))

Max Activating Token Index: 775

Text #18

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0072. Min Act: -0.0003

Data Index: 237801 (C4 (Web Text))

Max Activating Token Index: 173

Text #19

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0073. Min Act: -0.0003

Data Index: 553597 (C4 (Web Text))

Max Activating Token Index: 25