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

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

Neuron 587 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: 3.4693. Min Range: -3.4693

Max Act: 3.4693. Min Act: -0.0000

Data Index: 653673 (C4 (Web Text))

Max Activating Token Index: 323

Text #1

Max Range: 3.4693. Min Range: -3.4693

Max Act: 2.6396. Min Act: -0.0000

Data Index: 367236 (C4 (Web Text))

Max Activating Token Index: 379

Text #2

Max Range: 3.4693. Min Range: -3.4693

Max Act: 2.1943. Min Act: -0.0000

Data Index: 845076 (C4 (Web Text))

Max Activating Token Index: 438

Text #3

Max Range: 3.4693. Min Range: -3.4693

Max Act: 2.2513. Min Act: -0.0000

Data Index: 1261981 (C4 (Web Text))

Max Activating Token Index: 262

Text #4

Max Range: 3.4693. Min Range: -3.4693

Max Act: 2.1327. Min Act: -0.0000

Data Index: 684864 (C4 (Web Text))

Max Activating Token Index: 649

Text #5

Max Range: 3.4693. Min Range: -3.4693

Max Act: 2.0949. Min Act: -0.0000

Data Index: 367734 (C4 (Web Text))

Max Activating Token Index: 331

Text #6

Max Range: 3.4693. Min Range: -3.4693

Max Act: 1.8528. Min Act: -0.0000

Data Index: 843668 (C4 (Web Text))

Max Activating Token Index: 70

Text #7

Max Range: 3.4693. Min Range: -3.4693

Max Act: 1.9516. Min Act: -0.0000

Data Index: 574427 (C4 (Web Text))

Max Activating Token Index: 277

Text #8

Max Range: 3.4693. Min Range: -3.4693

Max Act: 1.7899. Min Act: -0.0000

Data Index: 1123064 (C4 (Web Text))

Max Activating Token Index: 479

Text #9

Max Range: 3.4693. Min Range: -3.4693

Max Act: 1.8944. Min Act: -0.0000

Data Index: 1052906 (C4 (Web Text))

Max Activating Token Index: 66

Text #10

Max Range: 3.4693. Min Range: -3.4693

Max Act: 1.8735. Min Act: -0.0000

Data Index: 940481 (C4 (Web Text))

Max Activating Token Index: 396

Text #11

Max Range: 3.4693. Min Range: -3.4693

Max Act: 1.6696. Min Act: -0.0000

Data Index: 1079640 (C4 (Web Text))

Max Activating Token Index: 221

Text #12

Max Range: 3.4693. Min Range: -3.4693

Max Act: 1.8156. Min Act: -0.0000

Data Index: 235276 (C4 (Web Text))

Max Activating Token Index: 965

Text #13

Max Range: 3.4693. Min Range: -3.4693

Max Act: 1.5832. Min Act: -0.0000

Data Index: 1002393 (C4 (Web Text))

Max Activating Token Index: 749

Text #14

Max Range: 3.4693. Min Range: -3.4693

Max Act: 1.8312. Min Act: -0.0000

Data Index: 1255753 (C4 (Web Text))

Max Activating Token Index: 289

Text #15

Max Range: 3.4693. Min Range: -3.4693

Max Act: 1.7826. Min Act: -0.0000

Data Index: 351713 (C4 (Web Text))

Max Activating Token Index: 556

Text #16

Max Range: 3.4693. Min Range: -3.4693

Max Act: 1.7593. Min Act: -0.0000

Data Index: 260359 (C4 (Web Text))

Max Activating Token Index: 662

Text #17

Max Range: 3.4693. Min Range: -3.4693

Max Act: 1.6825. Min Act: -0.0000

Data Index: 622265 (C4 (Web Text))

Max Activating Token Index: 365

Text #18

Max Range: 3.4693. Min Range: -3.4693

Max Act: 1.5741. Min Act: -0.0000

Data Index: 1312855 (C4 (Web Text))

Max Activating Token Index: 99

Text #19

Max Range: 3.4693. Min Range: -3.4693

Max Act: 1.6286. Min Act: -0.0000

Data Index: 1054840 (C4 (Web Text))

Max Activating Token Index: 435