Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1835 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3505. Min Range: -0.3505

Max Act: 0.3505. Min Act: -0.0000

Data Index: 728166 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 0.3505. Min Range: -0.3505

Max Act: 0.3455. Min Act: -0.0000

Data Index: 428470 (C4 (Web Text))

Max Activating Token Index: 9

Text #2

Max Range: 0.3505. Min Range: -0.3505

Max Act: 0.3201. Min Act: -0.0000

Data Index: 1124750 (C4 (Web Text))

Max Activating Token Index: 896

Text #3

Max Range: 0.3505. Min Range: -0.3505

Max Act: 0.3230. Min Act: -0.0000

Data Index: 571401 (C4 (Web Text))

Max Activating Token Index: 418

Text #4

Max Range: 0.3505. Min Range: -0.3505

Max Act: 0.3244. Min Act: -0.0000

Data Index: 726789 (C4 (Web Text))

Max Activating Token Index: 136

Text #5

Max Range: 0.3505. Min Range: -0.3505

Max Act: 0.3441. Min Act: -0.0000

Data Index: 1168870 (C4 (Web Text))

Max Activating Token Index: 315

Text #6

Max Range: 0.3505. Min Range: -0.3505

Max Act: 0.3072. Min Act: -0.0000

Data Index: 556859 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 0.3505. Min Range: -0.3505

Max Act: 0.3090. Min Act: -0.0000

Data Index: 862696 (C4 (Web Text))

Max Activating Token Index: 39

Text #8

Max Range: 0.3505. Min Range: -0.3505

Max Act: 0.2980. Min Act: -0.0000

Data Index: 444689 (C4 (Web Text))

Max Activating Token Index: 146

Text #9

Max Range: 0.3505. Min Range: -0.3505

Max Act: 0.2913. Min Act: -0.0000

Data Index: 1181182 (C4 (Web Text))

Max Activating Token Index: 158

Text #10

Max Range: 0.3505. Min Range: -0.3505

Max Act: 0.2864. Min Act: -0.0000

Data Index: 635339 (C4 (Web Text))

Max Activating Token Index: 73

Text #11

Max Range: 0.3505. Min Range: -0.3505

Max Act: 0.2869. Min Act: -0.0000

Data Index: 804434 (C4 (Web Text))

Max Activating Token Index: 153

Text #12

Max Range: 0.3505. Min Range: -0.3505

Max Act: 0.2858. Min Act: -0.0000

Data Index: 906024 (C4 (Web Text))

Max Activating Token Index: 28

Text #13

Max Range: 0.3505. Min Range: -0.3505

Max Act: 0.2849. Min Act: -0.0000

Data Index: 567763 (C4 (Web Text))

Max Activating Token Index: 940

Text #14

Max Range: 0.3505. Min Range: -0.3505

Max Act: 0.3022. Min Act: -0.0000

Data Index: 707498 (C4 (Web Text))

Max Activating Token Index: 736

Text #15

Max Range: 0.3505. Min Range: -0.3505

Max Act: 0.2329. Min Act: -0.0000

Data Index: 1573451 (Python Code)

Max Activating Token Index: 705

Text #16

Max Range: 0.3505. Min Range: -0.3505

Max Act: 0.2693. Min Act: -0.0000

Data Index: 643670 (C4 (Web Text))

Max Activating Token Index: 271

Text #17

Max Range: 0.3505. Min Range: -0.3505

Max Act: 0.2791. Min Act: -0.0000

Data Index: 1183250 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 0.3505. Min Range: -0.3505

Max Act: 0.2675. Min Act: -0.0000

Data Index: 151359 (C4 (Web Text))

Max Activating Token Index: 239

Text #19

Max Range: 0.3505. Min Range: -0.3505

Max Act: 0.2774. Min Act: -0.0000

Data Index: 1185494 (C4 (Web Text))

Max Activating Token Index: 118