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

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

Neuron 2536 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3196. Min Range: -3.3196

Max Act: 3.3196. Min Act: -0.0000

Data Index: 468587 (C4 (Web Text))

Max Activating Token Index: 1004

Text #1

Max Range: 3.3196. Min Range: -3.3196

Max Act: 2.9361. Min Act: -0.0000

Data Index: 1263399 (C4 (Web Text))

Max Activating Token Index: 762

Text #2

Max Range: 3.3196. Min Range: -3.3196

Max Act: 3.0992. Min Act: -0.0000

Data Index: 1204185 (C4 (Web Text))

Max Activating Token Index: 803

Text #3

Max Range: 3.3196. Min Range: -3.3196

Max Act: 2.6871. Min Act: -0.0000

Data Index: 976200 (C4 (Web Text))

Max Activating Token Index: 580

Text #4

Max Range: 3.3196. Min Range: -3.3196

Max Act: 1.8089. Min Act: -0.0000

Data Index: 776462 (C4 (Web Text))

Max Activating Token Index: 641

Text #5

Max Range: 3.3196. Min Range: -3.3196

Max Act: 1.6816. Min Act: -0.0000

Data Index: 763220 (C4 (Web Text))

Max Activating Token Index: 896

Text #6

Max Range: 3.3196. Min Range: -3.3196

Max Act: 1.4999. Min Act: -0.0000

Data Index: 719154 (C4 (Web Text))

Max Activating Token Index: 97

Text #7

Max Range: 3.3196. Min Range: -3.3196

Max Act: 1.3622. Min Act: -0.0000

Data Index: 181591 (C4 (Web Text))

Max Activating Token Index: 919

Text #8

Max Range: 3.3196. Min Range: -3.3196

Max Act: 1.2619. Min Act: -0.0000

Data Index: 937616 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 3.3196. Min Range: -3.3196

Max Act: 1.2922. Min Act: -0.0000

Data Index: 237329 (C4 (Web Text))

Max Activating Token Index: 473

Text #10

Max Range: 3.3196. Min Range: -3.3196

Max Act: 1.2146. Min Act: -0.0000

Data Index: 810063 (C4 (Web Text))

Max Activating Token Index: 133

Text #11

Max Range: 3.3196. Min Range: -3.3196

Max Act: 1.0942. Min Act: -0.0000

Data Index: 295609 (C4 (Web Text))

Max Activating Token Index: 204

Text #12

Max Range: 3.3196. Min Range: -3.3196

Max Act: 1.1648. Min Act: -0.0000

Data Index: 408090 (C4 (Web Text))

Max Activating Token Index: 809

Text #13

Max Range: 3.3196. Min Range: -3.3196

Max Act: 1.1322. Min Act: -0.0000

Data Index: 730615 (C4 (Web Text))

Max Activating Token Index: 170

Text #14

Max Range: 3.3196. Min Range: -3.3196

Max Act: 1.1065. Min Act: -0.0000

Data Index: 400157 (C4 (Web Text))

Max Activating Token Index: 835

Text #15

Max Range: 3.3196. Min Range: -3.3196

Max Act: 1.0023. Min Act: -0.0000

Data Index: 1030334 (C4 (Web Text))

Max Activating Token Index: 902

Text #16

Max Range: 3.3196. Min Range: -3.3196

Max Act: 1.0153. Min Act: -0.0000

Data Index: 1438737 (Python Code)

Max Activating Token Index: 647

Text #17

Max Range: 3.3196. Min Range: -3.3196

Max Act: 1.0924. Min Act: -0.0000

Data Index: 1120180 (C4 (Web Text))

Max Activating Token Index: 741

Text #18

Max Range: 3.3196. Min Range: -3.3196

Max Act: 0.9917. Min Act: -0.0000

Data Index: 817839 (C4 (Web Text))

Max Activating Token Index: 349

Text #19

Max Range: 3.3196. Min Range: -3.3196

Max Act: 0.9590. Min Act: -0.0000

Data Index: 969522 (C4 (Web Text))

Max Activating Token Index: 64