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

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

Neuron 2075 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4367. Min Range: -0.4367

Max Act: 0.4367. Min Act: 0.0000

Data Index: 115234 (C4 (Web Text))

Max Activating Token Index: 235

Text #1

Max Range: 0.4367. Min Range: -0.4367

Max Act: 0.3228. Min Act: -0.0000

Data Index: 64364 (C4 (Web Text))

Max Activating Token Index: 927

Text #2

Max Range: 0.4367. Min Range: -0.4367

Max Act: 0.2678. Min Act: -0.0000

Data Index: 719170 (C4 (Web Text))

Max Activating Token Index: 179

Text #3

Max Range: 0.4367. Min Range: -0.4367

Max Act: 0.2859. Min Act: -0.0000

Data Index: 1239396 (C4 (Web Text))

Max Activating Token Index: 219

Text #4

Max Range: 0.4367. Min Range: -0.4367

Max Act: 0.2845. Min Act: 0.0000

Data Index: 509998 (C4 (Web Text))

Max Activating Token Index: 503

Text #5

Max Range: 0.4367. Min Range: -0.4367

Max Act: 0.2641. Min Act: 0.0000

Data Index: 707653 (C4 (Web Text))

Max Activating Token Index: 246

Text #6

Max Range: 0.4367. Min Range: -0.4367

Max Act: 0.2708. Min Act: -0.0000

Data Index: 511008 (C4 (Web Text))

Max Activating Token Index: 303

Text #7

Max Range: 0.4367. Min Range: -0.4367

Max Act: 0.2689. Min Act: -0.0000

Data Index: 1332282 (C4 (Web Text))

Max Activating Token Index: 1006

Text #8

Max Range: 0.4367. Min Range: -0.4367

Max Act: 0.2700. Min Act: -0.0000

Data Index: 529859 (C4 (Web Text))

Max Activating Token Index: 294

Text #9

Max Range: 0.4367. Min Range: -0.4367

Max Act: 0.2673. Min Act: -0.0000

Data Index: 846364 (C4 (Web Text))

Max Activating Token Index: 139

Text #10

Max Range: 0.4367. Min Range: -0.4367

Max Act: 0.2666. Min Act: -0.0000

Data Index: 669286 (C4 (Web Text))

Max Activating Token Index: 955

Text #11

Max Range: 0.4367. Min Range: -0.4367

Max Act: 0.2651. Min Act: -0.0000

Data Index: 476504 (C4 (Web Text))

Max Activating Token Index: 801

Text #12

Max Range: 0.4367. Min Range: -0.4367

Max Act: 0.2809. Min Act: -0.0000

Data Index: 1251410 (C4 (Web Text))

Max Activating Token Index: 260

Text #13

Max Range: 0.4367. Min Range: -0.4367

Max Act: 0.2540. Min Act: -0.0000

Data Index: 98677 (C4 (Web Text))

Max Activating Token Index: 617

Text #14

Max Range: 0.4367. Min Range: -0.4367

Max Act: 0.2565. Min Act: -0.0000

Data Index: 402230 (C4 (Web Text))

Max Activating Token Index: 263

Text #15

Max Range: 0.4367. Min Range: -0.4367

Max Act: 0.2519. Min Act: -0.0000

Data Index: 916776 (C4 (Web Text))

Max Activating Token Index: 286

Text #16

Max Range: 0.4367. Min Range: -0.4367

Max Act: 0.2496. Min Act: -0.0000

Data Index: 675006 (C4 (Web Text))

Max Activating Token Index: 817

Text #17

Max Range: 0.4367. Min Range: -0.4367

Max Act: 0.2492. Min Act: -0.0000

Data Index: 255789 (C4 (Web Text))

Max Activating Token Index: 120

Text #18

Max Range: 0.4367. Min Range: -0.4367

Max Act: 0.2570. Min Act: -0.0000

Data Index: 888347 (C4 (Web Text))

Max Activating Token Index: 525

Text #19

Max Range: 0.4367. Min Range: -0.4367

Max Act: 0.2398. Min Act: -0.0000

Data Index: 1077994 (C4 (Web Text))

Max Activating Token Index: 798