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

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

Neuron 3505 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3515. Min Range: -0.3515

Max Act: 0.3515. Min Act: -0.0002

Data Index: 436475 (C4 (Web Text))

Max Activating Token Index: 751

Text #1

Max Range: 0.3515. Min Range: -0.3515

Max Act: 0.3218. Min Act: -0.0002

Data Index: 714952 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 0.3515. Min Range: -0.3515

Max Act: 0.2898. Min Act: -0.0002

Data Index: 1642725 (Python Code)

Max Activating Token Index: 272

Text #3

Max Range: 0.3515. Min Range: -0.3515

Max Act: 0.3326. Min Act: -0.0002

Data Index: 333869 (C4 (Web Text))

Max Activating Token Index: 803

Text #4

Max Range: 0.3515. Min Range: -0.3515

Max Act: 0.3094. Min Act: -0.0002

Data Index: 263820 (C4 (Web Text))

Max Activating Token Index: 159

Text #5

Max Range: 0.3515. Min Range: -0.3515

Max Act: 0.3198. Min Act: -0.0002

Data Index: 898048 (C4 (Web Text))

Max Activating Token Index: 950

Text #6

Max Range: 0.3515. Min Range: -0.3515

Max Act: 0.2894. Min Act: -0.0002

Data Index: 1056340 (C4 (Web Text))

Max Activating Token Index: 728

Text #7

Max Range: 0.3515. Min Range: -0.3515

Max Act: 0.2973. Min Act: -0.0002

Data Index: 317521 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 0.3515. Min Range: -0.3515

Max Act: 0.2779. Min Act: -0.0002

Data Index: 770166 (C4 (Web Text))

Max Activating Token Index: 264

Text #9

Max Range: 0.3515. Min Range: -0.3515

Max Act: 0.3023. Min Act: -0.0002

Data Index: 1157625 (C4 (Web Text))

Max Activating Token Index: 463

Text #10

Max Range: 0.3515. Min Range: -0.3515

Max Act: 0.2943. Min Act: -0.0002

Data Index: 138905 (C4 (Web Text))

Max Activating Token Index: 447

Text #11

Max Range: 0.3515. Min Range: -0.3515

Max Act: 0.2940. Min Act: -0.0002

Data Index: 477650 (C4 (Web Text))

Max Activating Token Index: 52

Text #12

Max Range: 0.3515. Min Range: -0.3515

Max Act: 0.3021. Min Act: -0.0002

Data Index: 699472 (C4 (Web Text))

Max Activating Token Index: 650

Text #13

Max Range: 0.3515. Min Range: -0.3515

Max Act: 0.2914. Min Act: -0.0002

Data Index: 379700 (C4 (Web Text))

Max Activating Token Index: 125

Text #14

Max Range: 0.3515. Min Range: -0.3515

Max Act: 0.2790. Min Act: -0.0002

Data Index: 421332 (C4 (Web Text))

Max Activating Token Index: 975

Text #15

Max Range: 0.3515. Min Range: -0.3515

Max Act: 0.3001. Min Act: -0.0002

Data Index: 1325460 (C4 (Web Text))

Max Activating Token Index: 58

Text #16

Max Range: 0.3515. Min Range: -0.3515

Max Act: 0.2872. Min Act: -0.0002

Data Index: 1235302 (C4 (Web Text))

Max Activating Token Index: 100

Text #17

Max Range: 0.3515. Min Range: -0.3515

Max Act: 0.3037. Min Act: -0.0002

Data Index: 111287 (C4 (Web Text))

Max Activating Token Index: 193

Text #18

Max Range: 0.3515. Min Range: -0.3515

Max Act: 0.2229. Min Act: -0.0002

Data Index: 1228092 (C4 (Web Text))

Max Activating Token Index: 332

Text #19

Max Range: 0.3515. Min Range: -0.3515

Max Act: 0.2590. Min Act: -0.0002

Data Index: 1310428 (C4 (Web Text))

Max Activating Token Index: 294