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

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

Neuron 5317 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.7032. Min Range: -6.7032

Max Act: 6.7032. Min Act: -0.0000

Data Index: 385369 (C4 (Web Text))

Max Activating Token Index: 215

Text #1

Max Range: 6.7032. Min Range: -6.7032

Max Act: 5.8026. Min Act: -0.0000

Data Index: 253025 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 6.7032. Min Range: -6.7032

Max Act: 5.2541. Min Act: -0.0000

Data Index: 1317212 (C4 (Web Text))

Max Activating Token Index: 656

Text #3

Max Range: 6.7032. Min Range: -6.7032

Max Act: 5.2052. Min Act: -0.0000

Data Index: 508582 (C4 (Web Text))

Max Activating Token Index: 549

Text #4

Max Range: 6.7032. Min Range: -6.7032

Max Act: 5.1387. Min Act: -0.0000

Data Index: 1133484 (C4 (Web Text))

Max Activating Token Index: 367

Text #5

Max Range: 6.7032. Min Range: -6.7032

Max Act: 4.5465. Min Act: -0.0000

Data Index: 17694 (C4 (Web Text))

Max Activating Token Index: 871

Text #6

Max Range: 6.7032. Min Range: -6.7032

Max Act: 4.5369. Min Act: -0.0000

Data Index: 594639 (C4 (Web Text))

Max Activating Token Index: 722

Text #7

Max Range: 6.7032. Min Range: -6.7032

Max Act: 4.7864. Min Act: -0.0000

Data Index: 1324280 (C4 (Web Text))

Max Activating Token Index: 858

Text #8

Max Range: 6.7032. Min Range: -6.7032

Max Act: 4.3700. Min Act: -0.0000

Data Index: 1265747 (C4 (Web Text))

Max Activating Token Index: 153

Text #9

Max Range: 6.7032. Min Range: -6.7032

Max Act: 4.3952. Min Act: -0.0000

Data Index: 53854 (C4 (Web Text))

Max Activating Token Index: 664

Text #10

Max Range: 6.7032. Min Range: -6.7032

Max Act: 4.4574. Min Act: -0.0000

Data Index: 668906 (C4 (Web Text))

Max Activating Token Index: 588

Text #11

Max Range: 6.7032. Min Range: -6.7032

Max Act: 4.2116. Min Act: -0.0000

Data Index: 207462 (C4 (Web Text))

Max Activating Token Index: 781

Text #12

Max Range: 6.7032. Min Range: -6.7032

Max Act: 4.5224. Min Act: -0.0000

Data Index: 1267901 (C4 (Web Text))

Max Activating Token Index: 368

Text #13

Max Range: 6.7032. Min Range: -6.7032

Max Act: 4.2219. Min Act: -0.0000

Data Index: 975394 (C4 (Web Text))

Max Activating Token Index: 186

Text #14

Max Range: 6.7032. Min Range: -6.7032

Max Act: 4.3345. Min Act: -0.0000

Data Index: 1147164 (C4 (Web Text))

Max Activating Token Index: 175

Text #15

Max Range: 6.7032. Min Range: -6.7032

Max Act: 3.9595. Min Act: -0.0000

Data Index: 951128 (C4 (Web Text))

Max Activating Token Index: 132

Text #16

Max Range: 6.7032. Min Range: -6.7032

Max Act: 3.9040. Min Act: -0.0000

Data Index: 1267460 (C4 (Web Text))

Max Activating Token Index: 231

Text #17

Max Range: 6.7032. Min Range: -6.7032

Max Act: 4.0646. Min Act: -0.0000

Data Index: 850006 (C4 (Web Text))

Max Activating Token Index: 328

Text #18

Max Range: 6.7032. Min Range: -6.7032

Max Act: 3.8696. Min Act: -0.0000

Data Index: 255274 (C4 (Web Text))

Max Activating Token Index: 507

Text #19

Max Range: 6.7032. Min Range: -6.7032

Max Act: 3.6007. Min Act: -0.0000

Data Index: 97622 (C4 (Web Text))

Max Activating Token Index: 753