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

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

Neuron 1653 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3499. Min Range: -5.3499

Max Act: 5.3499. Min Act: -0.0000

Data Index: 1318085 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 5.3499. Min Range: -5.3499

Max Act: 4.6390. Min Act: -0.0001

Data Index: 79167 (C4 (Web Text))

Max Activating Token Index: 637

Text #2

Max Range: 5.3499. Min Range: -5.3499

Max Act: 4.4521. Min Act: -0.0001

Data Index: 235142 (C4 (Web Text))

Max Activating Token Index: 497

Text #3

Max Range: 5.3499. Min Range: -5.3499

Max Act: 4.7972. Min Act: -0.0000

Data Index: 693404 (C4 (Web Text))

Max Activating Token Index: 475

Text #4

Max Range: 5.3499. Min Range: -5.3499

Max Act: 4.9371. Min Act: -0.0000

Data Index: 331192 (C4 (Web Text))

Max Activating Token Index: 447

Text #5

Max Range: 5.3499. Min Range: -5.3499

Max Act: 4.8247. Min Act: -0.0000

Data Index: 325833 (C4 (Web Text))

Max Activating Token Index: 583

Text #6

Max Range: 5.3499. Min Range: -5.3499

Max Act: 4.4502. Min Act: -0.0000

Data Index: 1168371 (C4 (Web Text))

Max Activating Token Index: 351

Text #7

Max Range: 5.3499. Min Range: -5.3499

Max Act: 4.6425. Min Act: -0.0000

Data Index: 1217078 (C4 (Web Text))

Max Activating Token Index: 561

Text #8

Max Range: 5.3499. Min Range: -5.3499

Max Act: 4.3849. Min Act: -0.0000

Data Index: 217664 (C4 (Web Text))

Max Activating Token Index: 24

Text #9

Max Range: 5.3499. Min Range: -5.3499

Max Act: 4.3983. Min Act: -0.0001

Data Index: 372185 (C4 (Web Text))

Max Activating Token Index: 620

Text #10

Max Range: 5.3499. Min Range: -5.3499

Max Act: 4.3407. Min Act: -0.0000

Data Index: 197160 (C4 (Web Text))

Max Activating Token Index: 136

Text #11

Max Range: 5.3499. Min Range: -5.3499

Max Act: 4.3907. Min Act: -0.0000

Data Index: 1094202 (C4 (Web Text))

Max Activating Token Index: 998

Text #12

Max Range: 5.3499. Min Range: -5.3499

Max Act: 4.1737. Min Act: -0.0000

Data Index: 27509 (C4 (Web Text))

Max Activating Token Index: 751

Text #13

Max Range: 5.3499. Min Range: -5.3499

Max Act: 4.4559. Min Act: -0.0000

Data Index: 598231 (C4 (Web Text))

Max Activating Token Index: 189

Text #14

Max Range: 5.3499. Min Range: -5.3499

Max Act: 4.5700. Min Act: -0.0001

Data Index: 145237 (C4 (Web Text))

Max Activating Token Index: 452

Text #15

Max Range: 5.3499. Min Range: -5.3499

Max Act: 3.8340. Min Act: -0.0000

Data Index: 777744 (C4 (Web Text))

Max Activating Token Index: 684

Text #16

Max Range: 5.3499. Min Range: -5.3499

Max Act: 4.4114. Min Act: -0.0000

Data Index: 437685 (C4 (Web Text))

Max Activating Token Index: 479

Text #17

Max Range: 5.3499. Min Range: -5.3499

Max Act: 4.0697. Min Act: -0.0000

Data Index: 1172684 (C4 (Web Text))

Max Activating Token Index: 402

Text #18

Max Range: 5.3499. Min Range: -5.3499

Max Act: 4.0365. Min Act: -0.0000

Data Index: 800906 (C4 (Web Text))

Max Activating Token Index: 20

Text #19

Max Range: 5.3499. Min Range: -5.3499

Max Act: 4.0376. Min Act: -0.0000

Data Index: 249058 (C4 (Web Text))

Max Activating Token Index: 175