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

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

Neuron 77 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1452. Min Range: -2.1452

Max Act: 2.1141. Min Act: -0.0000

Data Index: 1232810 (C4 (Web Text))

Max Activating Token Index: 320

Text #1

Max Range: 2.1452. Min Range: -2.1452

Max Act: 2.1452. Min Act: -0.0000

Data Index: 1198875 (C4 (Web Text))

Max Activating Token Index: 557

Text #2

Max Range: 2.1452. Min Range: -2.1452

Max Act: 2.0203. Min Act: -0.0000

Data Index: 1294737 (C4 (Web Text))

Max Activating Token Index: 949

Text #3

Max Range: 2.1452. Min Range: -2.1452

Max Act: 1.9148. Min Act: -0.0000

Data Index: 1124457 (C4 (Web Text))

Max Activating Token Index: 121

Text #4

Max Range: 2.1452. Min Range: -2.1452

Max Act: 1.8620. Min Act: -0.0000

Data Index: 269591 (C4 (Web Text))

Max Activating Token Index: 140

Text #5

Max Range: 2.1452. Min Range: -2.1452

Max Act: 2.0712. Min Act: -0.0000

Data Index: 365157 (C4 (Web Text))

Max Activating Token Index: 647

Text #6

Max Range: 2.1452. Min Range: -2.1452

Max Act: 1.9598. Min Act: -0.0000

Data Index: 738408 (C4 (Web Text))

Max Activating Token Index: 1009

Text #7

Max Range: 2.1452. Min Range: -2.1452

Max Act: 1.7865. Min Act: -0.0000

Data Index: 745843 (C4 (Web Text))

Max Activating Token Index: 353

Text #8

Max Range: 2.1452. Min Range: -2.1452

Max Act: 1.8604. Min Act: -0.0000

Data Index: 221881 (C4 (Web Text))

Max Activating Token Index: 649

Text #9

Max Range: 2.1452. Min Range: -2.1452

Max Act: 1.9314. Min Act: -0.0000

Data Index: 847515 (C4 (Web Text))

Max Activating Token Index: 717

Text #10

Max Range: 2.1452. Min Range: -2.1452

Max Act: 1.8133. Min Act: -0.0000

Data Index: 155139 (C4 (Web Text))

Max Activating Token Index: 320

Text #11

Max Range: 2.1452. Min Range: -2.1452

Max Act: 1.8958. Min Act: -0.0000

Data Index: 688119 (C4 (Web Text))

Max Activating Token Index: 111

Text #12

Max Range: 2.1452. Min Range: -2.1452

Max Act: 1.7034. Min Act: -0.0000

Data Index: 974642 (C4 (Web Text))

Max Activating Token Index: 235

Text #13

Max Range: 2.1452. Min Range: -2.1452

Max Act: 1.6561. Min Act: -0.0000

Data Index: 860256 (C4 (Web Text))

Max Activating Token Index: 343

Text #14

Max Range: 2.1452. Min Range: -2.1452

Max Act: 1.6141. Min Act: -0.0000

Data Index: 605644 (C4 (Web Text))

Max Activating Token Index: 838

Text #15

Max Range: 2.1452. Min Range: -2.1452

Max Act: 1.5900. Min Act: -0.0000

Data Index: 1129796 (C4 (Web Text))

Max Activating Token Index: 669

Text #16

Max Range: 2.1452. Min Range: -2.1452

Max Act: 1.6671. Min Act: -0.0000

Data Index: 933173 (C4 (Web Text))

Max Activating Token Index: 84

Text #17

Max Range: 2.1452. Min Range: -2.1452

Max Act: 1.6238. Min Act: -0.0000

Data Index: 596729 (C4 (Web Text))

Max Activating Token Index: 129

Text #18

Max Range: 2.1452. Min Range: -2.1452

Max Act: 1.7326. Min Act: -0.0000

Data Index: 955683 (C4 (Web Text))

Max Activating Token Index: 265

Text #19

Max Range: 2.1452. Min Range: -2.1452

Max Act: 1.7228. Min Act: -0.0000

Data Index: 592532 (C4 (Web Text))

Max Activating Token Index: 215