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

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

Neuron 2157 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: 0.3216. Min Range: -0.3216

Max Act: 0.3212. Min Act: -0.0001

Data Index: 472974 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 0.3216. Min Range: -0.3216

Max Act: 0.3071. Min Act: -0.0002

Data Index: 964689 (C4 (Web Text))

Max Activating Token Index: 392

Text #2

Max Range: 0.3216. Min Range: -0.3216

Max Act: 0.2899. Min Act: -0.0001

Data Index: 1573720 (Python Code)

Max Activating Token Index: 917

Text #3

Max Range: 0.3216. Min Range: -0.3216

Max Act: 0.2682. Min Act: -0.0002

Data Index: 619142 (C4 (Web Text))

Max Activating Token Index: 787

Text #4

Max Range: 0.3216. Min Range: -0.3216

Max Act: 0.2971. Min Act: -0.0002

Data Index: 1313820 (C4 (Web Text))

Max Activating Token Index: 381

Text #5

Max Range: 0.3216. Min Range: -0.3216

Max Act: 0.2934. Min Act: -0.0001

Data Index: 1397974 (Python Code)

Max Activating Token Index: 208

Text #6

Max Range: 0.3216. Min Range: -0.3216

Max Act: 0.2568. Min Act: -0.0001

Data Index: 1456121 (Python Code)

Max Activating Token Index: 990

Text #7

Max Range: 0.3216. Min Range: -0.3216

Max Act: 0.3216. Min Act: -0.0001

Data Index: 1365396 (Python Code)

Max Activating Token Index: 1017

Text #8

Max Range: 0.3216. Min Range: -0.3216

Max Act: 0.3116. Min Act: -0.0001

Data Index: 1459739 (Python Code)

Max Activating Token Index: 807

Text #9

Max Range: 0.3216. Min Range: -0.3216

Max Act: 0.2893. Min Act: -0.0001

Data Index: 1540865 (Python Code)

Max Activating Token Index: 68

Text #10

Max Range: 0.3216. Min Range: -0.3216

Max Act: 0.2991. Min Act: -0.0001

Data Index: 1238747 (C4 (Web Text))

Max Activating Token Index: 985

Text #11

Max Range: 0.3216. Min Range: -0.3216

Max Act: 0.2894. Min Act: -0.0001

Data Index: 1599526 (Python Code)

Max Activating Token Index: 167

Text #12

Max Range: 0.3216. Min Range: -0.3216

Max Act: 0.2962. Min Act: -0.0001

Data Index: 348733 (C4 (Web Text))

Max Activating Token Index: 579

Text #13

Max Range: 0.3216. Min Range: -0.3216

Max Act: 0.2515. Min Act: -0.0001

Data Index: 1375793 (Python Code)

Max Activating Token Index: 682

Text #14

Max Range: 0.3216. Min Range: -0.3216

Max Act: 0.2945. Min Act: -0.0002

Data Index: 189360 (C4 (Web Text))

Max Activating Token Index: 800

Text #15

Max Range: 0.3216. Min Range: -0.3216

Max Act: 0.2933. Min Act: -0.0001

Data Index: 1553935 (Python Code)

Max Activating Token Index: 108

Text #16

Max Range: 0.3216. Min Range: -0.3216

Max Act: 0.2718. Min Act: -0.0002

Data Index: 155508 (C4 (Web Text))

Max Activating Token Index: 549

Text #17

Max Range: 0.3216. Min Range: -0.3216

Max Act: 0.2881. Min Act: -0.0002

Data Index: 123037 (C4 (Web Text))

Max Activating Token Index: 342

Text #18

Max Range: 0.3216. Min Range: -0.3216

Max Act: 0.2867. Min Act: -0.0001

Data Index: 1543113 (Python Code)

Max Activating Token Index: 187

Text #19

Max Range: 0.3216. Min Range: -0.3216

Max Act: 0.2535. Min Act: -0.0002

Data Index: 254491 (C4 (Web Text))

Max Activating Token Index: 676