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

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

Neuron 3562 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7170. Min Range: -1.7170

Max Act: 1.7170. Min Act: -0.0000

Data Index: 1091862 (C4 (Web Text))

Max Activating Token Index: 837

Text #1

Max Range: 1.7170. Min Range: -1.7170

Max Act: 1.5425. Min Act: -0.0000

Data Index: 1356716 (C4 (Web Text))

Max Activating Token Index: 82

Text #2

Max Range: 1.7170. Min Range: -1.7170

Max Act: 1.3549. Min Act: -0.0000

Data Index: 1104467 (C4 (Web Text))

Max Activating Token Index: 485

Text #3

Max Range: 1.7170. Min Range: -1.7170

Max Act: 1.4963. Min Act: -0.0001

Data Index: 397563 (C4 (Web Text))

Max Activating Token Index: 97

Text #4

Max Range: 1.7170. Min Range: -1.7170

Max Act: 1.3649. Min Act: -0.0000

Data Index: 873410 (C4 (Web Text))

Max Activating Token Index: 243

Text #5

Max Range: 1.7170. Min Range: -1.7170

Max Act: 1.2518. Min Act: -0.0000

Data Index: 1075575 (C4 (Web Text))

Max Activating Token Index: 1013

Text #6

Max Range: 1.7170. Min Range: -1.7170

Max Act: 1.2230. Min Act: -0.0000

Data Index: 1085368 (C4 (Web Text))

Max Activating Token Index: 990

Text #7

Max Range: 1.7170. Min Range: -1.7170

Max Act: 1.3298. Min Act: -0.0000

Data Index: 1189383 (C4 (Web Text))

Max Activating Token Index: 840

Text #8

Max Range: 1.7170. Min Range: -1.7170

Max Act: 1.2795. Min Act: -0.0000

Data Index: 412437 (C4 (Web Text))

Max Activating Token Index: 755

Text #9

Max Range: 1.7170. Min Range: -1.7170

Max Act: 1.1154. Min Act: -0.0000

Data Index: 1183836 (C4 (Web Text))

Max Activating Token Index: 647

Text #10

Max Range: 1.7170. Min Range: -1.7170

Max Act: 1.2332. Min Act: -0.0000

Data Index: 267891 (C4 (Web Text))

Max Activating Token Index: 478

Text #11

Max Range: 1.7170. Min Range: -1.7170

Max Act: 1.1971. Min Act: -0.0000

Data Index: 464717 (C4 (Web Text))

Max Activating Token Index: 698

Text #12

Max Range: 1.7170. Min Range: -1.7170

Max Act: 1.1801. Min Act: -0.0000

Data Index: 265786 (C4 (Web Text))

Max Activating Token Index: 975

Text #13

Max Range: 1.7170. Min Range: -1.7170

Max Act: 1.1946. Min Act: -0.0000

Data Index: 1045190 (C4 (Web Text))

Max Activating Token Index: 819

Text #14

Max Range: 1.7170. Min Range: -1.7170

Max Act: 1.0841. Min Act: -0.0000

Data Index: 550659 (C4 (Web Text))

Max Activating Token Index: 426

Text #15

Max Range: 1.7170. Min Range: -1.7170

Max Act: 1.0798. Min Act: -0.0000

Data Index: 671394 (C4 (Web Text))

Max Activating Token Index: 929

Text #16

Max Range: 1.7170. Min Range: -1.7170

Max Act: 1.0053. Min Act: -0.0000

Data Index: 1341186 (C4 (Web Text))

Max Activating Token Index: 825

Text #17

Max Range: 1.7170. Min Range: -1.7170

Max Act: 1.1292. Min Act: -0.0001

Data Index: 967033 (C4 (Web Text))

Max Activating Token Index: 424

Text #18

Max Range: 1.7170. Min Range: -1.7170

Max Act: 1.0577. Min Act: -0.0000

Data Index: 409130 (C4 (Web Text))

Max Activating Token Index: 401

Text #19

Max Range: 1.7170. Min Range: -1.7170

Max Act: 1.0590. Min Act: -0.0001

Data Index: 426475 (C4 (Web Text))

Max Activating Token Index: 136