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

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

Neuron 3903 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4099. Min Range: -0.4099

Max Act: 0.4099. Min Act: -0.0000

Data Index: 589868 (C4 (Web Text))

Max Activating Token Index: 221

Text #1

Max Range: 0.4099. Min Range: -0.4099

Max Act: 0.3986. Min Act: -0.0000

Data Index: 70594 (C4 (Web Text))

Max Activating Token Index: 949

Text #2

Max Range: 0.4099. Min Range: -0.4099

Max Act: 0.3414. Min Act: -0.0000

Data Index: 1162897 (C4 (Web Text))

Max Activating Token Index: 1005

Text #3

Max Range: 0.4099. Min Range: -0.4099

Max Act: 0.3378. Min Act: -0.0000

Data Index: 1329915 (C4 (Web Text))

Max Activating Token Index: 692

Text #4

Max Range: 0.4099. Min Range: -0.4099

Max Act: 0.3413. Min Act: -0.0000

Data Index: 466119 (C4 (Web Text))

Max Activating Token Index: 239

Text #5

Max Range: 0.4099. Min Range: -0.4099

Max Act: 0.3400. Min Act: -0.0000

Data Index: 957485 (C4 (Web Text))

Max Activating Token Index: 642

Text #6

Max Range: 0.4099. Min Range: -0.4099

Max Act: 0.3445. Min Act: -0.0000

Data Index: 288646 (C4 (Web Text))

Max Activating Token Index: 882

Text #7

Max Range: 0.4099. Min Range: -0.4099

Max Act: 0.3217. Min Act: -0.0000

Data Index: 474380 (C4 (Web Text))

Max Activating Token Index: 619

Text #8

Max Range: 0.4099. Min Range: -0.4099

Max Act: 0.2919. Min Act: -0.0000

Data Index: 280051 (C4 (Web Text))

Max Activating Token Index: 582

Text #9

Max Range: 0.4099. Min Range: -0.4099

Max Act: 0.2959. Min Act: -0.0000

Data Index: 1335154 (C4 (Web Text))

Max Activating Token Index: 796

Text #10

Max Range: 0.4099. Min Range: -0.4099

Max Act: 0.2931. Min Act: -0.0000

Data Index: 636511 (C4 (Web Text))

Max Activating Token Index: 456

Text #11

Max Range: 0.4099. Min Range: -0.4099

Max Act: 0.3136. Min Act: -0.0000

Data Index: 755401 (C4 (Web Text))

Max Activating Token Index: 584

Text #12

Max Range: 0.4099. Min Range: -0.4099

Max Act: 0.2964. Min Act: -0.0000

Data Index: 108161 (C4 (Web Text))

Max Activating Token Index: 958

Text #13

Max Range: 0.4099. Min Range: -0.4099

Max Act: 0.2827. Min Act: -0.0000

Data Index: 774248 (C4 (Web Text))

Max Activating Token Index: 152

Text #14

Max Range: 0.4099. Min Range: -0.4099

Max Act: 0.2878. Min Act: -0.0000

Data Index: 552606 (C4 (Web Text))

Max Activating Token Index: 563

Text #15

Max Range: 0.4099. Min Range: -0.4099

Max Act: 0.2752. Min Act: -0.0000

Data Index: 615050 (C4 (Web Text))

Max Activating Token Index: 299

Text #16

Max Range: 0.4099. Min Range: -0.4099

Max Act: 0.2772. Min Act: -0.0000

Data Index: 1027951 (C4 (Web Text))

Max Activating Token Index: 352

Text #17

Max Range: 0.4099. Min Range: -0.4099

Max Act: 0.2823. Min Act: -0.0000

Data Index: 267565 (C4 (Web Text))

Max Activating Token Index: 434

Text #18

Max Range: 0.4099. Min Range: -0.4099

Max Act: 0.3040. Min Act: -0.0000

Data Index: 2325 (C4 (Web Text))

Max Activating Token Index: 762

Text #19

Max Range: 0.4099. Min Range: -0.4099

Max Act: 0.2840. Min Act: -0.0000

Data Index: 1249165 (C4 (Web Text))

Max Activating Token Index: 1015