Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 6139 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1147. Min Act: -0.0002

Data Index: 146829 (C4 (Web Text))

Max Activating Token Index: 175

Text #1

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1020. Min Act: -0.0002

Data Index: 915026 (C4 (Web Text))

Max Activating Token Index: 261

Text #2

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1059. Min Act: -0.0002

Data Index: 638209 (C4 (Web Text))

Max Activating Token Index: 578

Text #3

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1017. Min Act: -0.0002

Data Index: 90063 (C4 (Web Text))

Max Activating Token Index: 301

Text #4

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1003. Min Act: -0.0002

Data Index: 1133179 (C4 (Web Text))

Max Activating Token Index: 161

Text #5

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0994. Min Act: -0.0002

Data Index: 508218 (C4 (Web Text))

Max Activating Token Index: 676

Text #6

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0974. Min Act: -0.0002

Data Index: 126998 (C4 (Web Text))

Max Activating Token Index: 431

Text #7

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0965. Min Act: -0.0002

Data Index: 102930 (C4 (Web Text))

Max Activating Token Index: 719

Text #8

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0958. Min Act: -0.0002

Data Index: 483216 (C4 (Web Text))

Max Activating Token Index: 654

Text #9

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0948. Min Act: -0.0002

Data Index: 1050062 (C4 (Web Text))

Max Activating Token Index: 126

Text #10

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0947. Min Act: -0.0002

Data Index: 1096482 (C4 (Web Text))

Max Activating Token Index: 142

Text #11

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0916. Min Act: -0.0002

Data Index: 1127512 (C4 (Web Text))

Max Activating Token Index: 174

Text #12

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0927. Min Act: -0.0002

Data Index: 55766 (C4 (Web Text))

Max Activating Token Index: 663

Text #13

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0925. Min Act: -0.0002

Data Index: 918660 (C4 (Web Text))

Max Activating Token Index: 231

Text #14

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0912. Min Act: -0.0002

Data Index: 213730 (C4 (Web Text))

Max Activating Token Index: 428

Text #15

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0908. Min Act: -0.0002

Data Index: 546596 (C4 (Web Text))

Max Activating Token Index: 408

Text #16

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0901. Min Act: -0.0002

Data Index: 57951 (C4 (Web Text))

Max Activating Token Index: 727

Text #17

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0920. Min Act: -0.0002

Data Index: 1262303 (C4 (Web Text))

Max Activating Token Index: 177

Text #18

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0880. Min Act: -0.0002

Data Index: 587190 (C4 (Web Text))

Max Activating Token Index: 141

Text #19

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0882. Min Act: -0.0002

Data Index: 266781 (C4 (Web Text))

Max Activating Token Index: 460