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

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

Neuron 5050 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7857. Min Range: -3.7857

Max Act: 3.7857. Min Act: -0.0000

Data Index: 382193 (C4 (Web Text))

Max Activating Token Index: 741

Text #1

Max Range: 3.7857. Min Range: -3.7857

Max Act: 3.6312. Min Act: -0.0000

Data Index: 769843 (C4 (Web Text))

Max Activating Token Index: 506

Text #2

Max Range: 3.7857. Min Range: -3.7857

Max Act: 2.9448. Min Act: -0.0000

Data Index: 236579 (C4 (Web Text))

Max Activating Token Index: 330

Text #3

Max Range: 3.7857. Min Range: -3.7857

Max Act: 2.9202. Min Act: -0.0000

Data Index: 142472 (C4 (Web Text))

Max Activating Token Index: 498

Text #4

Max Range: 3.7857. Min Range: -3.7857

Max Act: 2.6874. Min Act: -0.0000

Data Index: 1015308 (C4 (Web Text))

Max Activating Token Index: 639

Text #5

Max Range: 3.7857. Min Range: -3.7857

Max Act: 3.0420. Min Act: -0.0000

Data Index: 951083 (C4 (Web Text))

Max Activating Token Index: 360

Text #6

Max Range: 3.7857. Min Range: -3.7857

Max Act: 2.4693. Min Act: -0.0000

Data Index: 502575 (C4 (Web Text))

Max Activating Token Index: 963

Text #7

Max Range: 3.7857. Min Range: -3.7857

Max Act: 2.5249. Min Act: -0.0000

Data Index: 827057 (C4 (Web Text))

Max Activating Token Index: 467

Text #8

Max Range: 3.7857. Min Range: -3.7857

Max Act: 2.5740. Min Act: -0.0000

Data Index: 442330 (C4 (Web Text))

Max Activating Token Index: 671

Text #9

Max Range: 3.7857. Min Range: -3.7857

Max Act: 2.4939. Min Act: -0.0000

Data Index: 1353131 (C4 (Web Text))

Max Activating Token Index: 39

Text #10

Max Range: 3.7857. Min Range: -3.7857

Max Act: 2.4566. Min Act: -0.0000

Data Index: 1352451 (C4 (Web Text))

Max Activating Token Index: 167

Text #11

Max Range: 3.7857. Min Range: -3.7857

Max Act: 2.4197. Min Act: -0.0000

Data Index: 253174 (C4 (Web Text))

Max Activating Token Index: 467

Text #12

Max Range: 3.7857. Min Range: -3.7857

Max Act: 2.3828. Min Act: -0.0000

Data Index: 640400 (C4 (Web Text))

Max Activating Token Index: 392

Text #13

Max Range: 3.7857. Min Range: -3.7857

Max Act: 2.3587. Min Act: -0.0000

Data Index: 1324002 (C4 (Web Text))

Max Activating Token Index: 696

Text #14

Max Range: 3.7857. Min Range: -3.7857

Max Act: 2.3217. Min Act: -0.0000

Data Index: 809940 (C4 (Web Text))

Max Activating Token Index: 289

Text #15

Max Range: 3.7857. Min Range: -3.7857

Max Act: 2.2730. Min Act: -0.0000

Data Index: 212680 (C4 (Web Text))

Max Activating Token Index: 758

Text #16

Max Range: 3.7857. Min Range: -3.7857

Max Act: 2.5115. Min Act: -0.0000

Data Index: 976188 (C4 (Web Text))

Max Activating Token Index: 714

Text #17

Max Range: 3.7857. Min Range: -3.7857

Max Act: 2.1549. Min Act: -0.0000

Data Index: 56861 (C4 (Web Text))

Max Activating Token Index: 949

Text #18

Max Range: 3.7857. Min Range: -3.7857

Max Act: 2.1434. Min Act: -0.0000

Data Index: 81539 (C4 (Web Text))

Max Activating Token Index: 380

Text #19

Max Range: 3.7857. Min Range: -3.7857

Max Act: 2.1385. Min Act: -0.0000

Data Index: 308187 (C4 (Web Text))

Max Activating Token Index: 668