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

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

Neuron 2908 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3247. Min Range: -0.3247

Max Act: 0.3048. Min Act: -0.0001

Data Index: 1454383 (Python Code)

Max Activating Token Index: 579

Text #1

Max Range: 0.3247. Min Range: -0.3247

Max Act: 0.3247. Min Act: -0.0001

Data Index: 1362233 (Python Code)

Max Activating Token Index: 478

Text #2

Max Range: 0.3247. Min Range: -0.3247

Max Act: 0.3168. Min Act: -0.0001

Data Index: 1652998 (Python Code)

Max Activating Token Index: 67

Text #3

Max Range: 0.3247. Min Range: -0.3247

Max Act: 0.3185. Min Act: -0.0001

Data Index: 1621485 (Python Code)

Max Activating Token Index: 357

Text #4

Max Range: 0.3247. Min Range: -0.3247

Max Act: 0.2865. Min Act: -0.0001

Data Index: 1593257 (Python Code)

Max Activating Token Index: 689

Text #5

Max Range: 0.3247. Min Range: -0.3247

Max Act: 0.2843. Min Act: -0.0001

Data Index: 1517182 (Python Code)

Max Activating Token Index: 409

Text #6

Max Range: 0.3247. Min Range: -0.3247

Max Act: 0.3039. Min Act: -0.0001

Data Index: 1369109 (Python Code)

Max Activating Token Index: 466

Text #7

Max Range: 0.3247. Min Range: -0.3247

Max Act: 0.3029. Min Act: -0.0001

Data Index: 1365396 (Python Code)

Max Activating Token Index: 269

Text #8

Max Range: 0.3247. Min Range: -0.3247

Max Act: 0.2926. Min Act: -0.0001

Data Index: 1531631 (Python Code)

Max Activating Token Index: 106

Text #9

Max Range: 0.3247. Min Range: -0.3247

Max Act: 0.3143. Min Act: -0.0001

Data Index: 1468557 (Python Code)

Max Activating Token Index: 215

Text #10

Max Range: 0.3247. Min Range: -0.3247

Max Act: 0.2745. Min Act: -0.0001

Data Index: 1607071 (Python Code)

Max Activating Token Index: 260

Text #11

Max Range: 0.3247. Min Range: -0.3247

Max Act: 0.2767. Min Act: -0.0001

Data Index: 1508627 (Python Code)

Max Activating Token Index: 895

Text #12

Max Range: 0.3247. Min Range: -0.3247

Max Act: 0.2958. Min Act: -0.0001

Data Index: 1403679 (Python Code)

Max Activating Token Index: 367

Text #13

Max Range: 0.3247. Min Range: -0.3247

Max Act: 0.2780. Min Act: -0.0001

Data Index: 1563588 (Python Code)

Max Activating Token Index: 354

Text #14

Max Range: 0.3247. Min Range: -0.3247

Max Act: 0.2890. Min Act: -0.0001

Data Index: 1519079 (Python Code)

Max Activating Token Index: 24

Text #15

Max Range: 0.3247. Min Range: -0.3247

Max Act: 0.2602. Min Act: -0.0001

Data Index: 1500722 (Python Code)

Max Activating Token Index: 219

Text #16

Max Range: 0.3247. Min Range: -0.3247

Max Act: 0.2776. Min Act: -0.0001

Data Index: 1602270 (Python Code)

Max Activating Token Index: 117

Text #17

Max Range: 0.3247. Min Range: -0.3247

Max Act: 0.2644. Min Act: -0.0001

Data Index: 1532139 (Python Code)

Max Activating Token Index: 53

Text #18

Max Range: 0.3247. Min Range: -0.3247

Max Act: 0.2828. Min Act: -0.0001

Data Index: 1372680 (Python Code)

Max Activating Token Index: 88

Text #19

Max Range: 0.3247. Min Range: -0.3247

Max Act: 0.2732. Min Act: -0.0001

Data Index: 1541630 (Python Code)

Max Activating Token Index: 366