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

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

Neuron 45 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4814. Min Range: -1.4814

Max Act: 1.4814. Min Act: -0.0000

Data Index: 64382 (C4 (Web Text))

Max Activating Token Index: 484

Text #1

Max Range: 1.4814. Min Range: -1.4814

Max Act: 1.1384. Min Act: -0.0000

Data Index: 1399440 (Python Code)

Max Activating Token Index: 755

Text #2

Max Range: 1.4814. Min Range: -1.4814

Max Act: 1.1679. Min Act: -0.0000

Data Index: 1108910 (C4 (Web Text))

Max Activating Token Index: 826

Text #3

Max Range: 1.4814. Min Range: -1.4814

Max Act: 1.3179. Min Act: -0.0000

Data Index: 96090 (C4 (Web Text))

Max Activating Token Index: 257

Text #4

Max Range: 1.4814. Min Range: -1.4814

Max Act: 0.9857. Min Act: -0.0000

Data Index: 859880 (C4 (Web Text))

Max Activating Token Index: 384

Text #5

Max Range: 1.4814. Min Range: -1.4814

Max Act: 0.9139. Min Act: -0.0000

Data Index: 1069888 (C4 (Web Text))

Max Activating Token Index: 924

Text #6

Max Range: 1.4814. Min Range: -1.4814

Max Act: 0.9020. Min Act: -0.0000

Data Index: 444350 (C4 (Web Text))

Max Activating Token Index: 415

Text #7

Max Range: 1.4814. Min Range: -1.4814

Max Act: 0.9621. Min Act: -0.0000

Data Index: 1150814 (C4 (Web Text))

Max Activating Token Index: 555

Text #8

Max Range: 1.4814. Min Range: -1.4814

Max Act: 0.9126. Min Act: -0.0000

Data Index: 1139014 (C4 (Web Text))

Max Activating Token Index: 596

Text #9

Max Range: 1.4814. Min Range: -1.4814

Max Act: 0.9097. Min Act: -0.0000

Data Index: 36421 (C4 (Web Text))

Max Activating Token Index: 198

Text #10

Max Range: 1.4814. Min Range: -1.4814

Max Act: 0.9301. Min Act: -0.0000

Data Index: 262544 (C4 (Web Text))

Max Activating Token Index: 221

Text #11

Max Range: 1.4814. Min Range: -1.4814

Max Act: 0.8457. Min Act: -0.0000

Data Index: 1356985 (C4 (Web Text))

Max Activating Token Index: 482

Text #12

Max Range: 1.4814. Min Range: -1.4814

Max Act: 0.8617. Min Act: -0.0000

Data Index: 276475 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 1.4814. Min Range: -1.4814

Max Act: 0.8056. Min Act: -0.0000

Data Index: 763188 (C4 (Web Text))

Max Activating Token Index: 581

Text #14

Max Range: 1.4814. Min Range: -1.4814

Max Act: 0.8601. Min Act: -0.0000

Data Index: 1358291 (C4 (Web Text))

Max Activating Token Index: 407

Text #15

Max Range: 1.4814. Min Range: -1.4814

Max Act: 0.8036. Min Act: -0.0000

Data Index: 1274073 (C4 (Web Text))

Max Activating Token Index: 587

Text #16

Max Range: 1.4814. Min Range: -1.4814

Max Act: 0.8384. Min Act: -0.0000

Data Index: 503436 (C4 (Web Text))

Max Activating Token Index: 847

Text #17

Max Range: 1.4814. Min Range: -1.4814

Max Act: 0.7985. Min Act: -0.0000

Data Index: 1329458 (C4 (Web Text))

Max Activating Token Index: 430

Text #18

Max Range: 1.4814. Min Range: -1.4814

Max Act: 0.8510. Min Act: -0.0000

Data Index: 1244066 (C4 (Web Text))

Max Activating Token Index: 126

Text #19

Max Range: 1.4814. Min Range: -1.4814

Max Act: 0.7722. Min Act: -0.0000

Data Index: 81688 (C4 (Web Text))

Max Activating Token Index: 196