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

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

Neuron 2394 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: 0.9144. Min Range: -0.9144

Max Act: 0.9144. Min Act: -0.0000

Data Index: 775695 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 0.9144. Min Range: -0.9144

Max Act: 0.8946. Min Act: -0.0000

Data Index: 1143830 (C4 (Web Text))

Max Activating Token Index: 403

Text #2

Max Range: 0.9144. Min Range: -0.9144

Max Act: 0.8576. Min Act: -0.0000

Data Index: 238795 (C4 (Web Text))

Max Activating Token Index: 372

Text #3

Max Range: 0.9144. Min Range: -0.9144

Max Act: 0.7745. Min Act: -0.0000

Data Index: 175462 (C4 (Web Text))

Max Activating Token Index: 845

Text #4

Max Range: 0.9144. Min Range: -0.9144

Max Act: 0.8171. Min Act: -0.0000

Data Index: 403945 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 0.9144. Min Range: -0.9144

Max Act: 0.6652. Min Act: -0.0000

Data Index: 902618 (C4 (Web Text))

Max Activating Token Index: 949

Text #6

Max Range: 0.9144. Min Range: -0.9144

Max Act: 0.6652. Min Act: -0.0000

Data Index: 1409179 (Python Code)

Max Activating Token Index: 768

Text #7

Max Range: 0.9144. Min Range: -0.9144

Max Act: 0.6174. Min Act: -0.0000

Data Index: 375489 (C4 (Web Text))

Max Activating Token Index: 210

Text #8

Max Range: 0.9144. Min Range: -0.9144

Max Act: 0.6327. Min Act: -0.0000

Data Index: 1324041 (C4 (Web Text))

Max Activating Token Index: 453

Text #9

Max Range: 0.9144. Min Range: -0.9144

Max Act: 0.6340. Min Act: -0.0000

Data Index: 600441 (C4 (Web Text))

Max Activating Token Index: 714

Text #10

Max Range: 0.9144. Min Range: -0.9144

Max Act: 0.6261. Min Act: -0.0000

Data Index: 1229421 (C4 (Web Text))

Max Activating Token Index: 13

Text #11

Max Range: 0.9144. Min Range: -0.9144

Max Act: 0.5997. Min Act: -0.0000

Data Index: 833480 (C4 (Web Text))

Max Activating Token Index: 910

Text #12

Max Range: 0.9144. Min Range: -0.9144

Max Act: 0.6422. Min Act: -0.0000

Data Index: 1038749 (C4 (Web Text))

Max Activating Token Index: 825

Text #13

Max Range: 0.9144. Min Range: -0.9144

Max Act: 0.6044. Min Act: -0.0000

Data Index: 1002883 (C4 (Web Text))

Max Activating Token Index: 734

Text #14

Max Range: 0.9144. Min Range: -0.9144

Max Act: 0.5859. Min Act: -0.0000

Data Index: 1178153 (C4 (Web Text))

Max Activating Token Index: 922

Text #15

Max Range: 0.9144. Min Range: -0.9144

Max Act: 0.5120. Min Act: -0.0000

Data Index: 1316196 (C4 (Web Text))

Max Activating Token Index: 284

Text #16

Max Range: 0.9144. Min Range: -0.9144

Max Act: 0.4285. Min Act: -0.0000

Data Index: 1215821 (C4 (Web Text))

Max Activating Token Index: 950

Text #17

Max Range: 0.9144. Min Range: -0.9144

Max Act: 0.5296. Min Act: -0.0000

Data Index: 347099 (C4 (Web Text))

Max Activating Token Index: 170

Text #18

Max Range: 0.9144. Min Range: -0.9144

Max Act: 0.4436. Min Act: -0.0000

Data Index: 621726 (C4 (Web Text))

Max Activating Token Index: 292

Text #19

Max Range: 0.9144. Min Range: -0.9144

Max Act: 0.5051. Min Act: -0.0000

Data Index: 64721 (C4 (Web Text))

Max Activating Token Index: 885