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

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

Neuron 2417 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: 0.1784. Min Range: -0.1784

Max Act: 0.1784. Min Act: -0.0002

Data Index: 419270 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1130. Min Act: -0.0001

Data Index: 1350136 (C4 (Web Text))

Max Activating Token Index: 872

Text #2

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1024. Min Act: -0.0001

Data Index: 711661 (C4 (Web Text))

Max Activating Token Index: 917

Text #3

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1009. Min Act: -0.0002

Data Index: 632272 (C4 (Web Text))

Max Activating Token Index: 744

Text #4

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1003. Min Act: -0.0001

Data Index: 511708 (C4 (Web Text))

Max Activating Token Index: 685

Text #5

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.0906. Min Act: -0.0002

Data Index: 573765 (C4 (Web Text))

Max Activating Token Index: 857

Text #6

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.0881. Min Act: -0.0002

Data Index: 589133 (C4 (Web Text))

Max Activating Token Index: 619

Text #7

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.0847. Min Act: -0.0002

Data Index: 397254 (C4 (Web Text))

Max Activating Token Index: 723

Text #8

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.0802. Min Act: -0.0001

Data Index: 1221835 (C4 (Web Text))

Max Activating Token Index: 873

Text #9

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.0854. Min Act: -0.0001

Data Index: 94189 (C4 (Web Text))

Max Activating Token Index: 585

Text #10

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.0883. Min Act: -0.0001

Data Index: 514147 (C4 (Web Text))

Max Activating Token Index: 431

Text #11

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.0849. Min Act: -0.0002

Data Index: 387228 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.0842. Min Act: -0.0002

Data Index: 431892 (C4 (Web Text))

Max Activating Token Index: 185

Text #13

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.0840. Min Act: -0.0001

Data Index: 271162 (C4 (Web Text))

Max Activating Token Index: 340

Text #14

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.0789. Min Act: -0.0001

Data Index: 519270 (C4 (Web Text))

Max Activating Token Index: 77

Text #15

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.0821. Min Act: -0.0001

Data Index: 1105879 (C4 (Web Text))

Max Activating Token Index: 318

Text #16

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.0843. Min Act: -0.0002

Data Index: 1048030 (C4 (Web Text))

Max Activating Token Index: 378

Text #17

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.0775. Min Act: -0.0001

Data Index: 1130204 (C4 (Web Text))

Max Activating Token Index: 49

Text #18

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.0805. Min Act: -0.0001

Data Index: 157245 (C4 (Web Text))

Max Activating Token Index: 195

Text #19

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.0866. Min Act: -0.0001

Data Index: 245939 (C4 (Web Text))

Max Activating Token Index: 673