Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 766 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.2467. Min Range: -2.2467

Max Act: 2.2467. Min Act: -0.0000

Data Index: 1171012 (C4 (Web Text))

Max Activating Token Index: 568

Text #1

Max Range: 2.2467. Min Range: -2.2467

Max Act: 2.1583. Min Act: -0.0000

Data Index: 1029650 (C4 (Web Text))

Max Activating Token Index: 121

Text #2

Max Range: 2.2467. Min Range: -2.2467

Max Act: 1.9937. Min Act: -0.0000

Data Index: 677784 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 2.2467. Min Range: -2.2467

Max Act: 1.8922. Min Act: -0.0000

Data Index: 13028 (C4 (Web Text))

Max Activating Token Index: 353

Text #4

Max Range: 2.2467. Min Range: -2.2467

Max Act: 2.1202. Min Act: -0.0000

Data Index: 196187 (C4 (Web Text))

Max Activating Token Index: 246

Text #5

Max Range: 2.2467. Min Range: -2.2467

Max Act: 1.9699. Min Act: -0.0000

Data Index: 569961 (C4 (Web Text))

Max Activating Token Index: 216

Text #6

Max Range: 2.2467. Min Range: -2.2467

Max Act: 1.7064. Min Act: -0.0000

Data Index: 566649 (C4 (Web Text))

Max Activating Token Index: 513

Text #7

Max Range: 2.2467. Min Range: -2.2467

Max Act: 1.7338. Min Act: -0.0000

Data Index: 670367 (C4 (Web Text))

Max Activating Token Index: 193

Text #8

Max Range: 2.2467. Min Range: -2.2467

Max Act: 1.6568. Min Act: -0.0000

Data Index: 1098302 (C4 (Web Text))

Max Activating Token Index: 103

Text #9

Max Range: 2.2467. Min Range: -2.2467

Max Act: 1.5986. Min Act: 0.0000

Data Index: 316680 (C4 (Web Text))

Max Activating Token Index: 556

Text #10

Max Range: 2.2467. Min Range: -2.2467

Max Act: 1.5651. Min Act: -0.0000

Data Index: 1249071 (C4 (Web Text))

Max Activating Token Index: 5

Text #11

Max Range: 2.2467. Min Range: -2.2467

Max Act: 1.3435. Min Act: -0.0000

Data Index: 426081 (C4 (Web Text))

Max Activating Token Index: 786

Text #12

Max Range: 2.2467. Min Range: -2.2467

Max Act: 1.4441. Min Act: -0.0000

Data Index: 48941 (C4 (Web Text))

Max Activating Token Index: 265

Text #13

Max Range: 2.2467. Min Range: -2.2467

Max Act: 1.4150. Min Act: -0.0000

Data Index: 251920 (C4 (Web Text))

Max Activating Token Index: 723

Text #14

Max Range: 2.2467. Min Range: -2.2467

Max Act: 1.3945. Min Act: -0.0000

Data Index: 953727 (C4 (Web Text))

Max Activating Token Index: 496

Text #15

Max Range: 2.2467. Min Range: -2.2467

Max Act: 1.2999. Min Act: -0.0000

Data Index: 1276900 (C4 (Web Text))

Max Activating Token Index: 836

Text #16

Max Range: 2.2467. Min Range: -2.2467

Max Act: 1.2677. Min Act: -0.0000

Data Index: 385070 (C4 (Web Text))

Max Activating Token Index: 903

Text #17

Max Range: 2.2467. Min Range: -2.2467

Max Act: 1.2921. Min Act: -0.0000

Data Index: 566055 (C4 (Web Text))

Max Activating Token Index: 999

Text #18

Max Range: 2.2467. Min Range: -2.2467

Max Act: 1.3494. Min Act: -0.0000

Data Index: 1185338 (C4 (Web Text))

Max Activating Token Index: 385

Text #19

Max Range: 2.2467. Min Range: -2.2467

Max Act: 1.3337. Min Act: -0.0000

Data Index: 250877 (C4 (Web Text))

Max Activating Token Index: 70