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

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

Neuron 1876 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: 0.1178. Min Range: -0.1178

Max Act: 0.1178. Min Act: -0.0001

Data Index: 1429865 (Python Code)

Max Activating Token Index: 408

Text #1

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.1066. Min Act: -0.0001

Data Index: 1547200 (Python Code)

Max Activating Token Index: 69

Text #2

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.1118. Min Act: -0.0001

Data Index: 187138 (C4 (Web Text))

Max Activating Token Index: 927

Text #3

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.1038. Min Act: -0.0001

Data Index: 1648056 (Python Code)

Max Activating Token Index: 712

Text #4

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0990. Min Act: -0.0001

Data Index: 1526443 (Python Code)

Max Activating Token Index: 785

Text #5

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0989. Min Act: -0.0001

Data Index: 1406568 (Python Code)

Max Activating Token Index: 22

Text #6

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0988. Min Act: -0.0002

Data Index: 835340 (C4 (Web Text))

Max Activating Token Index: 79

Text #7

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.1058. Min Act: -0.0002

Data Index: 947501 (C4 (Web Text))

Max Activating Token Index: 372

Text #8

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0829. Min Act: -0.0002

Data Index: 588103 (C4 (Web Text))

Max Activating Token Index: 378

Text #9

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.1003. Min Act: -0.0002

Data Index: 457156 (C4 (Web Text))

Max Activating Token Index: 313

Text #10

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0874. Min Act: -0.0001

Data Index: 512663 (C4 (Web Text))

Max Activating Token Index: 653

Text #11

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0922. Min Act: -0.0001

Data Index: 1588699 (Python Code)

Max Activating Token Index: 130

Text #12

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0907. Min Act: -0.0001

Data Index: 950523 (C4 (Web Text))

Max Activating Token Index: 949

Text #13

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0916. Min Act: -0.0001

Data Index: 847569 (C4 (Web Text))

Max Activating Token Index: 152

Text #14

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0851. Min Act: -0.0002

Data Index: 61359 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0932. Min Act: -0.0002

Data Index: 1188170 (C4 (Web Text))

Max Activating Token Index: 629

Text #16

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0780. Min Act: -0.0002

Data Index: 5104 (C4 (Web Text))

Max Activating Token Index: 884

Text #17

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0898. Min Act: -0.0002

Data Index: 837259 (C4 (Web Text))

Max Activating Token Index: 929

Text #18

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0730. Min Act: -0.0002

Data Index: 31494 (C4 (Web Text))

Max Activating Token Index: 807

Text #19

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0867. Min Act: -0.0001

Data Index: 272065 (C4 (Web Text))

Max Activating Token Index: 31