Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2216 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.1142. Min Range: -1.1142

Max Act: 1.1089. Min Act: -0.0001

Data Index: 510597 (C4 (Web Text))

Max Activating Token Index: 488

Text #1

Max Range: 1.1142. Min Range: -1.1142

Max Act: 1.1142. Min Act: -0.0001

Data Index: 1424565 (Python Code)

Max Activating Token Index: 50

Text #2

Max Range: 1.1142. Min Range: -1.1142

Max Act: 1.0655. Min Act: -0.0001

Data Index: 332605 (C4 (Web Text))

Max Activating Token Index: 69

Text #3

Max Range: 1.1142. Min Range: -1.1142

Max Act: 1.0186. Min Act: -0.0001

Data Index: 1413185 (Python Code)

Max Activating Token Index: 254

Text #4

Max Range: 1.1142. Min Range: -1.1142

Max Act: 0.9775. Min Act: -0.0001

Data Index: 861147 (C4 (Web Text))

Max Activating Token Index: 735

Text #5

Max Range: 1.1142. Min Range: -1.1142

Max Act: 0.8594. Min Act: -0.0001

Data Index: 1628140 (Python Code)

Max Activating Token Index: 158

Text #6

Max Range: 1.1142. Min Range: -1.1142

Max Act: 0.8199. Min Act: -0.0001

Data Index: 1354944 (C4 (Web Text))

Max Activating Token Index: 573

Text #7

Max Range: 1.1142. Min Range: -1.1142

Max Act: 0.8178. Min Act: -0.0001

Data Index: 916459 (C4 (Web Text))

Max Activating Token Index: 394

Text #8

Max Range: 1.1142. Min Range: -1.1142

Max Act: 0.8584. Min Act: -0.0001

Data Index: 1306817 (C4 (Web Text))

Max Activating Token Index: 92

Text #9

Max Range: 1.1142. Min Range: -1.1142

Max Act: 0.8537. Min Act: -0.0001

Data Index: 1628710 (Python Code)

Max Activating Token Index: 18

Text #10

Max Range: 1.1142. Min Range: -1.1142

Max Act: 0.8694. Min Act: -0.0001

Data Index: 603422 (C4 (Web Text))

Max Activating Token Index: 5

Text #11

Max Range: 1.1142. Min Range: -1.1142

Max Act: 0.8173. Min Act: -0.0001

Data Index: 731830 (C4 (Web Text))

Max Activating Token Index: 320

Text #12

Max Range: 1.1142. Min Range: -1.1142

Max Act: 0.8349. Min Act: -0.0001

Data Index: 174406 (C4 (Web Text))

Max Activating Token Index: 168

Text #13

Max Range: 1.1142. Min Range: -1.1142

Max Act: 0.8173. Min Act: -0.0001

Data Index: 3000 (C4 (Web Text))

Max Activating Token Index: 34

Text #14

Max Range: 1.1142. Min Range: -1.1142

Max Act: 0.8180. Min Act: -0.0001

Data Index: 208749 (C4 (Web Text))

Max Activating Token Index: 251

Text #15

Max Range: 1.1142. Min Range: -1.1142

Max Act: 0.7867. Min Act: -0.0001

Data Index: 361870 (C4 (Web Text))

Max Activating Token Index: 21

Text #16

Max Range: 1.1142. Min Range: -1.1142

Max Act: 0.7562. Min Act: -0.0001

Data Index: 118934 (C4 (Web Text))

Max Activating Token Index: 410

Text #17

Max Range: 1.1142. Min Range: -1.1142

Max Act: 0.7705. Min Act: -0.0001

Data Index: 1118370 (C4 (Web Text))

Max Activating Token Index: 791

Text #18

Max Range: 1.1142. Min Range: -1.1142

Max Act: 0.7999. Min Act: -0.0001

Data Index: 278512 (C4 (Web Text))

Max Activating Token Index: 857

Text #19

Max Range: 1.1142. Min Range: -1.1142

Max Act: 0.7918. Min Act: -0.0001

Data Index: 1059624 (C4 (Web Text))

Max Activating Token Index: 469