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

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

Neuron 216 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6797. Min Range: -2.6797

Max Act: 2.6797. Min Act: -0.0000

Data Index: 920216 (C4 (Web Text))

Max Activating Token Index: 643

Text #1

Max Range: 2.6797. Min Range: -2.6797

Max Act: 2.3288. Min Act: -0.0000

Data Index: 1108638 (C4 (Web Text))

Max Activating Token Index: 205

Text #2

Max Range: 2.6797. Min Range: -2.6797

Max Act: 2.2741. Min Act: -0.0001

Data Index: 1269861 (C4 (Web Text))

Max Activating Token Index: 63

Text #3

Max Range: 2.6797. Min Range: -2.6797

Max Act: 2.1287. Min Act: -0.0000

Data Index: 1198966 (C4 (Web Text))

Max Activating Token Index: 405

Text #4

Max Range: 2.6797. Min Range: -2.6797

Max Act: 2.2330. Min Act: -0.0001

Data Index: 465381 (C4 (Web Text))

Max Activating Token Index: 124

Text #5

Max Range: 2.6797. Min Range: -2.6797

Max Act: 2.2335. Min Act: -0.0001

Data Index: 186392 (C4 (Web Text))

Max Activating Token Index: 386

Text #6

Max Range: 2.6797. Min Range: -2.6797

Max Act: 2.1261. Min Act: -0.0000

Data Index: 1110666 (C4 (Web Text))

Max Activating Token Index: 314

Text #7

Max Range: 2.6797. Min Range: -2.6797

Max Act: 2.0833. Min Act: -0.0000

Data Index: 984824 (C4 (Web Text))

Max Activating Token Index: 442

Text #8

Max Range: 2.6797. Min Range: -2.6797

Max Act: 2.0410. Min Act: -0.0000

Data Index: 1340809 (C4 (Web Text))

Max Activating Token Index: 806

Text #9

Max Range: 2.6797. Min Range: -2.6797

Max Act: 2.0239. Min Act: -0.0000

Data Index: 802565 (C4 (Web Text))

Max Activating Token Index: 848

Text #10

Max Range: 2.6797. Min Range: -2.6797

Max Act: 2.0144. Min Act: -0.0001

Data Index: 929333 (C4 (Web Text))

Max Activating Token Index: 96

Text #11

Max Range: 2.6797. Min Range: -2.6797

Max Act: 1.9713. Min Act: -0.0000

Data Index: 1357726 (C4 (Web Text))

Max Activating Token Index: 621

Text #12

Max Range: 2.6797. Min Range: -2.6797

Max Act: 2.0814. Min Act: -0.0000

Data Index: 399110 (C4 (Web Text))

Max Activating Token Index: 555

Text #13

Max Range: 2.6797. Min Range: -2.6797

Max Act: 2.0671. Min Act: -0.0000

Data Index: 816282 (C4 (Web Text))

Max Activating Token Index: 493

Text #14

Max Range: 2.6797. Min Range: -2.6797

Max Act: 2.1772. Min Act: -0.0000

Data Index: 934806 (C4 (Web Text))

Max Activating Token Index: 161

Text #15

Max Range: 2.6797. Min Range: -2.6797

Max Act: 1.9276. Min Act: -0.0000

Data Index: 644160 (C4 (Web Text))

Max Activating Token Index: 360

Text #16

Max Range: 2.6797. Min Range: -2.6797

Max Act: 2.1553. Min Act: -0.0001

Data Index: 160067 (C4 (Web Text))

Max Activating Token Index: 362

Text #17

Max Range: 2.6797. Min Range: -2.6797

Max Act: 2.0278. Min Act: -0.0000

Data Index: 460664 (C4 (Web Text))

Max Activating Token Index: 185

Text #18

Max Range: 2.6797. Min Range: -2.6797

Max Act: 2.2655. Min Act: -0.0000

Data Index: 200900 (C4 (Web Text))

Max Activating Token Index: 240

Text #19

Max Range: 2.6797. Min Range: -2.6797

Max Act: 2.1274. Min Act: -0.0001

Data Index: 1211203 (C4 (Web Text))

Max Activating Token Index: 791