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

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

Neuron 4455 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6247. Min Range: -0.6247

Max Act: 0.5946. Min Act: -0.0000

Data Index: 816070 (C4 (Web Text))

Max Activating Token Index: 262

Text #1

Max Range: 0.6247. Min Range: -0.6247

Max Act: 0.6247. Min Act: -0.0000

Data Index: 1354880 (C4 (Web Text))

Max Activating Token Index: 325

Text #2

Max Range: 0.6247. Min Range: -0.6247

Max Act: 0.5845. Min Act: -0.0000

Data Index: 1038547 (C4 (Web Text))

Max Activating Token Index: 418

Text #3

Max Range: 0.6247. Min Range: -0.6247

Max Act: 0.5644. Min Act: -0.0000

Data Index: 1355057 (C4 (Web Text))

Max Activating Token Index: 817

Text #4

Max Range: 0.6247. Min Range: -0.6247

Max Act: 0.5740. Min Act: -0.0000

Data Index: 543479 (C4 (Web Text))

Max Activating Token Index: 954

Text #5

Max Range: 0.6247. Min Range: -0.6247

Max Act: 0.5584. Min Act: -0.0000

Data Index: 599804 (C4 (Web Text))

Max Activating Token Index: 191

Text #6

Max Range: 0.6247. Min Range: -0.6247

Max Act: 0.5363. Min Act: -0.0000

Data Index: 1026098 (C4 (Web Text))

Max Activating Token Index: 191

Text #7

Max Range: 0.6247. Min Range: -0.6247

Max Act: 0.5169. Min Act: -0.0000

Data Index: 1510755 (Python Code)

Max Activating Token Index: 16

Text #8

Max Range: 0.6247. Min Range: -0.6247

Max Act: 0.4821. Min Act: -0.0000

Data Index: 1229746 (C4 (Web Text))

Max Activating Token Index: 86

Text #9

Max Range: 0.6247. Min Range: -0.6247

Max Act: 0.4994. Min Act: -0.0000

Data Index: 1176777 (C4 (Web Text))

Max Activating Token Index: 66

Text #10

Max Range: 0.6247. Min Range: -0.6247

Max Act: 0.4798. Min Act: -0.0000

Data Index: 107044 (C4 (Web Text))

Max Activating Token Index: 253

Text #11

Max Range: 0.6247. Min Range: -0.6247

Max Act: 0.4964. Min Act: -0.0000

Data Index: 94318 (C4 (Web Text))

Max Activating Token Index: 767

Text #12

Max Range: 0.6247. Min Range: -0.6247

Max Act: 0.4918. Min Act: -0.0000

Data Index: 364531 (C4 (Web Text))

Max Activating Token Index: 84

Text #13

Max Range: 0.6247. Min Range: -0.6247

Max Act: 0.4866. Min Act: -0.0000

Data Index: 1076973 (C4 (Web Text))

Max Activating Token Index: 218

Text #14

Max Range: 0.6247. Min Range: -0.6247

Max Act: 0.4686. Min Act: -0.0000

Data Index: 1277045 (C4 (Web Text))

Max Activating Token Index: 177

Text #15

Max Range: 0.6247. Min Range: -0.6247

Max Act: 0.4598. Min Act: -0.0000

Data Index: 1579313 (Python Code)

Max Activating Token Index: 23

Text #16

Max Range: 0.6247. Min Range: -0.6247

Max Act: 0.4744. Min Act: -0.0000

Data Index: 856379 (C4 (Web Text))

Max Activating Token Index: 445

Text #17

Max Range: 0.6247. Min Range: -0.6247

Max Act: 0.4606. Min Act: -0.0000

Data Index: 540662 (C4 (Web Text))

Max Activating Token Index: 449

Text #18

Max Range: 0.6247. Min Range: -0.6247

Max Act: 0.4741. Min Act: -0.0000

Data Index: 636652 (C4 (Web Text))

Max Activating Token Index: 965

Text #19

Max Range: 0.6247. Min Range: -0.6247

Max Act: 0.4792. Min Act: -0.0000

Data Index: 809150 (C4 (Web Text))

Max Activating Token Index: 236