Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1422 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.6802. Min Act: -0.0003

Data Index: 602251 (C4 (Web Text))

Max Activating Token Index: 84

Text #1

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.6611. Min Act: -0.0003

Data Index: 426432 (C4 (Web Text))

Max Activating Token Index: 97

Text #2

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.5412. Min Act: -0.0003

Data Index: 584562 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.5771. Min Act: -0.0003

Data Index: 593067 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.5658. Min Act: -0.0003

Data Index: 27990 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.5504. Min Act: -0.0002

Data Index: 226255 (C4 (Web Text))

Max Activating Token Index: 107

Text #6

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.5392. Min Act: -0.0003

Data Index: 1073428 (C4 (Web Text))

Max Activating Token Index: 600

Text #7

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.5549. Min Act: -0.0003

Data Index: 495076 (C4 (Web Text))

Max Activating Token Index: 90

Text #8

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.5230. Min Act: -0.0003

Data Index: 1236057 (C4 (Web Text))

Max Activating Token Index: 73

Text #9

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.5169. Min Act: -0.0003

Data Index: 1077539 (C4 (Web Text))

Max Activating Token Index: 433

Text #10

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.5272. Min Act: -0.0003

Data Index: 840057 (C4 (Web Text))

Max Activating Token Index: 106

Text #11

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.5003. Min Act: -0.0003

Data Index: 14341 (C4 (Web Text))

Max Activating Token Index: 75

Text #12

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.5174. Min Act: -0.0003

Data Index: 637320 (C4 (Web Text))

Max Activating Token Index: 104

Text #13

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.4975. Min Act: -0.0003

Data Index: 617579 (C4 (Web Text))

Max Activating Token Index: 986

Text #14

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.4941. Min Act: -0.0002

Data Index: 626810 (C4 (Web Text))

Max Activating Token Index: 21

Text #15

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.4915. Min Act: -0.0003

Data Index: 156482 (C4 (Web Text))

Max Activating Token Index: 132

Text #16

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.5119. Min Act: -0.0003

Data Index: 274137 (C4 (Web Text))

Max Activating Token Index: 88

Text #17

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.5076. Min Act: -0.0003

Data Index: 559311 (C4 (Web Text))

Max Activating Token Index: 79

Text #18

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.5088. Min Act: -0.0003

Data Index: 300624 (C4 (Web Text))

Max Activating Token Index: 7

Text #19

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.4829. Min Act: -0.0003

Data Index: 1199379 (C4 (Web Text))

Max Activating Token Index: 263