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

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

Neuron 2584 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0844. Min Range: -2.0844

Max Act: 2.0844. Min Act: -0.0000

Data Index: 73149 (C4 (Web Text))

Max Activating Token Index: 99

Text #1

Max Range: 2.0844. Min Range: -2.0844

Max Act: 1.7152. Min Act: -0.0000

Data Index: 538531 (C4 (Web Text))

Max Activating Token Index: 114

Text #2

Max Range: 2.0844. Min Range: -2.0844

Max Act: 1.6822. Min Act: -0.0000

Data Index: 156912 (C4 (Web Text))

Max Activating Token Index: 829

Text #3

Max Range: 2.0844. Min Range: -2.0844

Max Act: 1.6215. Min Act: -0.0000

Data Index: 1306293 (C4 (Web Text))

Max Activating Token Index: 917

Text #4

Max Range: 2.0844. Min Range: -2.0844

Max Act: 1.5986. Min Act: -0.0000

Data Index: 808802 (C4 (Web Text))

Max Activating Token Index: 204

Text #5

Max Range: 2.0844. Min Range: -2.0844

Max Act: 1.6795. Min Act: -0.0001

Data Index: 131015 (C4 (Web Text))

Max Activating Token Index: 919

Text #6

Max Range: 2.0844. Min Range: -2.0844

Max Act: 1.5671. Min Act: -0.0000

Data Index: 1304260 (C4 (Web Text))

Max Activating Token Index: 561

Text #7

Max Range: 2.0844. Min Range: -2.0844

Max Act: 1.5712. Min Act: -0.0000

Data Index: 3931 (C4 (Web Text))

Max Activating Token Index: 321

Text #8

Max Range: 2.0844. Min Range: -2.0844

Max Act: 1.6861. Min Act: -0.0000

Data Index: 1126650 (C4 (Web Text))

Max Activating Token Index: 741

Text #9

Max Range: 2.0844. Min Range: -2.0844

Max Act: 1.6318. Min Act: -0.0001

Data Index: 168302 (C4 (Web Text))

Max Activating Token Index: 809

Text #10

Max Range: 2.0844. Min Range: -2.0844

Max Act: 1.5866. Min Act: -0.0000

Data Index: 785382 (C4 (Web Text))

Max Activating Token Index: 341

Text #11

Max Range: 2.0844. Min Range: -2.0844

Max Act: 1.5384. Min Act: -0.0001

Data Index: 397576 (C4 (Web Text))

Max Activating Token Index: 391

Text #12

Max Range: 2.0844. Min Range: -2.0844

Max Act: 1.6581. Min Act: -0.0000

Data Index: 809771 (C4 (Web Text))

Max Activating Token Index: 971

Text #13

Max Range: 2.0844. Min Range: -2.0844

Max Act: 1.5443. Min Act: -0.0001

Data Index: 1107867 (C4 (Web Text))

Max Activating Token Index: 237

Text #14

Max Range: 2.0844. Min Range: -2.0844

Max Act: 1.6087. Min Act: -0.0000

Data Index: 1404281 (Python Code)

Max Activating Token Index: 66

Text #15

Max Range: 2.0844. Min Range: -2.0844

Max Act: 1.6005. Min Act: -0.0000

Data Index: 761605 (C4 (Web Text))

Max Activating Token Index: 306

Text #16

Max Range: 2.0844. Min Range: -2.0844

Max Act: 1.5749. Min Act: -0.0000

Data Index: 174958 (C4 (Web Text))

Max Activating Token Index: 784

Text #17

Max Range: 2.0844. Min Range: -2.0844

Max Act: 1.5036. Min Act: -0.0000

Data Index: 75828 (C4 (Web Text))

Max Activating Token Index: 804

Text #18

Max Range: 2.0844. Min Range: -2.0844

Max Act: 1.5979. Min Act: -0.0000

Data Index: 418615 (C4 (Web Text))

Max Activating Token Index: 270

Text #19

Max Range: 2.0844. Min Range: -2.0844

Max Act: 1.5342. Min Act: -0.0000

Data Index: 1196618 (C4 (Web Text))

Max Activating Token Index: 943