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

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

Neuron 889 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5324. Min Range: -2.5324

Max Act: 2.5324. Min Act: -0.0000

Data Index: 661080 (C4 (Web Text))

Max Activating Token Index: 286

Text #1

Max Range: 2.5324. Min Range: -2.5324

Max Act: 2.4941. Min Act: -0.0000

Data Index: 1167938 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 2.5324. Min Range: -2.5324

Max Act: 2.4123. Min Act: -0.0000

Data Index: 96013 (C4 (Web Text))

Max Activating Token Index: 189

Text #3

Max Range: 2.5324. Min Range: -2.5324

Max Act: 2.3151. Min Act: -0.0000

Data Index: 167241 (C4 (Web Text))

Max Activating Token Index: 1013

Text #4

Max Range: 2.5324. Min Range: -2.5324

Max Act: 2.2709. Min Act: -0.0000

Data Index: 544723 (C4 (Web Text))

Max Activating Token Index: 220

Text #5

Max Range: 2.5324. Min Range: -2.5324

Max Act: 2.1782. Min Act: -0.0000

Data Index: 70674 (C4 (Web Text))

Max Activating Token Index: 268

Text #6

Max Range: 2.5324. Min Range: -2.5324

Max Act: 2.0933. Min Act: -0.0000

Data Index: 216669 (C4 (Web Text))

Max Activating Token Index: 94

Text #7

Max Range: 2.5324. Min Range: -2.5324

Max Act: 2.0987. Min Act: -0.0000

Data Index: 473510 (C4 (Web Text))

Max Activating Token Index: 936

Text #8

Max Range: 2.5324. Min Range: -2.5324

Max Act: 1.9386. Min Act: -0.0000

Data Index: 1041262 (C4 (Web Text))

Max Activating Token Index: 318

Text #9

Max Range: 2.5324. Min Range: -2.5324

Max Act: 2.1320. Min Act: -0.0000

Data Index: 966328 (C4 (Web Text))

Max Activating Token Index: 674

Text #10

Max Range: 2.5324. Min Range: -2.5324

Max Act: 1.9096. Min Act: -0.0000

Data Index: 800262 (C4 (Web Text))

Max Activating Token Index: 224

Text #11

Max Range: 2.5324. Min Range: -2.5324

Max Act: 2.0134. Min Act: -0.0000

Data Index: 700568 (C4 (Web Text))

Max Activating Token Index: 991

Text #12

Max Range: 2.5324. Min Range: -2.5324

Max Act: 2.0033. Min Act: -0.0000

Data Index: 1318404 (C4 (Web Text))

Max Activating Token Index: 570

Text #13

Max Range: 2.5324. Min Range: -2.5324

Max Act: 1.9720. Min Act: -0.0000

Data Index: 1170418 (C4 (Web Text))

Max Activating Token Index: 994

Text #14

Max Range: 2.5324. Min Range: -2.5324

Max Act: 1.9729. Min Act: -0.0000

Data Index: 58095 (C4 (Web Text))

Max Activating Token Index: 891

Text #15

Max Range: 2.5324. Min Range: -2.5324

Max Act: 1.8702. Min Act: -0.0000

Data Index: 878774 (C4 (Web Text))

Max Activating Token Index: 960

Text #16

Max Range: 2.5324. Min Range: -2.5324

Max Act: 1.9444. Min Act: -0.0000

Data Index: 31603 (C4 (Web Text))

Max Activating Token Index: 782

Text #17

Max Range: 2.5324. Min Range: -2.5324

Max Act: 1.8469. Min Act: -0.0000

Data Index: 235486 (C4 (Web Text))

Max Activating Token Index: 519

Text #18

Max Range: 2.5324. Min Range: -2.5324

Max Act: 1.8270. Min Act: -0.0000

Data Index: 292273 (C4 (Web Text))

Max Activating Token Index: 487

Text #19

Max Range: 2.5324. Min Range: -2.5324

Max Act: 1.9319. Min Act: -0.0000

Data Index: 115566 (C4 (Web Text))

Max Activating Token Index: 128