Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 194 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4080. Min Range: -0.4080

Max Act: 0.4042. Min Act: -0.0000

Data Index: 974911 (C4 (Web Text))

Max Activating Token Index: 856

Text #1

Max Range: 0.4080. Min Range: -0.4080

Max Act: 0.3922. Min Act: -0.0000

Data Index: 793845 (C4 (Web Text))

Max Activating Token Index: 883

Text #2

Max Range: 0.4080. Min Range: -0.4080

Max Act: 0.3905. Min Act: -0.0000

Data Index: 1304685 (C4 (Web Text))

Max Activating Token Index: 219

Text #3

Max Range: 0.4080. Min Range: -0.4080

Max Act: 0.3656. Min Act: -0.0000

Data Index: 375906 (C4 (Web Text))

Max Activating Token Index: 690

Text #4

Max Range: 0.4080. Min Range: -0.4080

Max Act: 0.4080. Min Act: -0.0000

Data Index: 530701 (C4 (Web Text))

Max Activating Token Index: 160

Text #5

Max Range: 0.4080. Min Range: -0.4080

Max Act: 0.3310. Min Act: -0.0000

Data Index: 396211 (C4 (Web Text))

Max Activating Token Index: 291

Text #6

Max Range: 0.4080. Min Range: -0.4080

Max Act: 0.3864. Min Act: -0.0000

Data Index: 1051276 (C4 (Web Text))

Max Activating Token Index: 884

Text #7

Max Range: 0.4080. Min Range: -0.4080

Max Act: 0.3424. Min Act: -0.0000

Data Index: 879124 (C4 (Web Text))

Max Activating Token Index: 704

Text #8

Max Range: 0.4080. Min Range: -0.4080

Max Act: 0.3452. Min Act: -0.0000

Data Index: 1230297 (C4 (Web Text))

Max Activating Token Index: 167

Text #9

Max Range: 0.4080. Min Range: -0.4080

Max Act: 0.3321. Min Act: -0.0000

Data Index: 190041 (C4 (Web Text))

Max Activating Token Index: 835

Text #10

Max Range: 0.4080. Min Range: -0.4080

Max Act: 0.3261. Min Act: -0.0000

Data Index: 852206 (C4 (Web Text))

Max Activating Token Index: 361

Text #11

Max Range: 0.4080. Min Range: -0.4080

Max Act: 0.3386. Min Act: -0.0000

Data Index: 296704 (C4 (Web Text))

Max Activating Token Index: 819

Text #12

Max Range: 0.4080. Min Range: -0.4080

Max Act: 0.2900. Min Act: -0.0000

Data Index: 1131515 (C4 (Web Text))

Max Activating Token Index: 327

Text #13

Max Range: 0.4080. Min Range: -0.4080

Max Act: 0.3097. Min Act: -0.0000

Data Index: 691932 (C4 (Web Text))

Max Activating Token Index: 108

Text #14

Max Range: 0.4080. Min Range: -0.4080

Max Act: 0.3096. Min Act: -0.0000

Data Index: 9811 (C4 (Web Text))

Max Activating Token Index: 784

Text #15

Max Range: 0.4080. Min Range: -0.4080

Max Act: 0.2945. Min Act: -0.0000

Data Index: 983511 (C4 (Web Text))

Max Activating Token Index: 349

Text #16

Max Range: 0.4080. Min Range: -0.4080

Max Act: 0.3043. Min Act: -0.0000

Data Index: 1014440 (C4 (Web Text))

Max Activating Token Index: 622

Text #17

Max Range: 0.4080. Min Range: -0.4080

Max Act: 0.2897. Min Act: -0.0000

Data Index: 744936 (C4 (Web Text))

Max Activating Token Index: 232

Text #18

Max Range: 0.4080. Min Range: -0.4080

Max Act: 0.2760. Min Act: -0.0000

Data Index: 1330159 (C4 (Web Text))

Max Activating Token Index: 952

Text #19

Max Range: 0.4080. Min Range: -0.4080

Max Act: 0.2864. Min Act: -0.0000

Data Index: 1122062 (C4 (Web Text))

Max Activating Token Index: 140