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

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

Neuron 1024 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9300. Min Range: -1.9300

Max Act: 1.9300. Min Act: -0.0000

Data Index: 1047969 (C4 (Web Text))

Max Activating Token Index: 418

Text #1

Max Range: 1.9300. Min Range: -1.9300

Max Act: 1.6141. Min Act: -0.0000

Data Index: 971725 (C4 (Web Text))

Max Activating Token Index: 118

Text #2

Max Range: 1.9300. Min Range: -1.9300

Max Act: 1.4545. Min Act: -0.0000

Data Index: 560693 (C4 (Web Text))

Max Activating Token Index: 196

Text #3

Max Range: 1.9300. Min Range: -1.9300

Max Act: 1.5050. Min Act: -0.0000

Data Index: 83851 (C4 (Web Text))

Max Activating Token Index: 126

Text #4

Max Range: 1.9300. Min Range: -1.9300

Max Act: 1.5077. Min Act: -0.0000

Data Index: 593930 (C4 (Web Text))

Max Activating Token Index: 692

Text #5

Max Range: 1.9300. Min Range: -1.9300

Max Act: 1.5142. Min Act: -0.0000

Data Index: 78682 (C4 (Web Text))

Max Activating Token Index: 689

Text #6

Max Range: 1.9300. Min Range: -1.9300

Max Act: 1.4501. Min Act: -0.0000

Data Index: 1205324 (C4 (Web Text))

Max Activating Token Index: 1001

Text #7

Max Range: 1.9300. Min Range: -1.9300

Max Act: 1.2162. Min Act: -0.0000

Data Index: 457760 (C4 (Web Text))

Max Activating Token Index: 92

Text #8

Max Range: 1.9300. Min Range: -1.9300

Max Act: 1.1169. Min Act: -0.0000

Data Index: 375104 (C4 (Web Text))

Max Activating Token Index: 922

Text #9

Max Range: 1.9300. Min Range: -1.9300

Max Act: 1.0475. Min Act: -0.0000

Data Index: 566401 (C4 (Web Text))

Max Activating Token Index: 602

Text #10

Max Range: 1.9300. Min Range: -1.9300

Max Act: 1.0829. Min Act: -0.0000

Data Index: 501595 (C4 (Web Text))

Max Activating Token Index: 538

Text #11

Max Range: 1.9300. Min Range: -1.9300

Max Act: 0.9719. Min Act: -0.0000

Data Index: 265912 (C4 (Web Text))

Max Activating Token Index: 1005

Text #12

Max Range: 1.9300. Min Range: -1.9300

Max Act: 0.8445. Min Act: -0.0000

Data Index: 872742 (C4 (Web Text))

Max Activating Token Index: 1006

Text #13

Max Range: 1.9300. Min Range: -1.9300

Max Act: 0.8367. Min Act: 0.0000

Data Index: 573488 (C4 (Web Text))

Max Activating Token Index: 78

Text #14

Max Range: 1.9300. Min Range: -1.9300

Max Act: 0.8336. Min Act: -0.0000

Data Index: 3135 (C4 (Web Text))

Max Activating Token Index: 672

Text #15

Max Range: 1.9300. Min Range: -1.9300

Max Act: 0.8675. Min Act: -0.0000

Data Index: 429452 (C4 (Web Text))

Max Activating Token Index: 286

Text #16

Max Range: 1.9300. Min Range: -1.9300

Max Act: 0.7940. Min Act: -0.0000

Data Index: 717286 (C4 (Web Text))

Max Activating Token Index: 632

Text #17

Max Range: 1.9300. Min Range: -1.9300

Max Act: 0.7752. Min Act: -0.0000

Data Index: 900071 (C4 (Web Text))

Max Activating Token Index: 890

Text #18

Max Range: 1.9300. Min Range: -1.9300

Max Act: 0.7593. Min Act: -0.0000

Data Index: 1143479 (C4 (Web Text))

Max Activating Token Index: 877

Text #19

Max Range: 1.9300. Min Range: -1.9300

Max Act: 0.7382. Min Act: -0.0000

Data Index: 1325324 (C4 (Web Text))

Max Activating Token Index: 801