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

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

Neuron 5882 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4572. Min Range: -2.4572

Max Act: 2.4572. Min Act: -0.0000

Data Index: 1368902 (Python Code)

Max Activating Token Index: 966

Text #1

Max Range: 2.4572. Min Range: -2.4572

Max Act: 2.2189. Min Act: -0.0000

Data Index: 1071907 (C4 (Web Text))

Max Activating Token Index: 252

Text #2

Max Range: 2.4572. Min Range: -2.4572

Max Act: 2.2385. Min Act: -0.0000

Data Index: 1459253 (Python Code)

Max Activating Token Index: 966

Text #3

Max Range: 2.4572. Min Range: -2.4572

Max Act: 2.0394. Min Act: -0.0000

Data Index: 1258488 (C4 (Web Text))

Max Activating Token Index: 899

Text #4

Max Range: 2.4572. Min Range: -2.4572

Max Act: 1.7601. Min Act: -0.0000

Data Index: 1048699 (C4 (Web Text))

Max Activating Token Index: 929

Text #5

Max Range: 2.4572. Min Range: -2.4572

Max Act: 1.9409. Min Act: -0.0000

Data Index: 384947 (C4 (Web Text))

Max Activating Token Index: 507

Text #6

Max Range: 2.4572. Min Range: -2.4572

Max Act: 1.9440. Min Act: -0.0000

Data Index: 179394 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 2.4572. Min Range: -2.4572

Max Act: 1.9099. Min Act: -0.0000

Data Index: 1351470 (C4 (Web Text))

Max Activating Token Index: 1012

Text #8

Max Range: 2.4572. Min Range: -2.4572

Max Act: 2.0124. Min Act: -0.0000

Data Index: 420097 (C4 (Web Text))

Max Activating Token Index: 885

Text #9

Max Range: 2.4572. Min Range: -2.4572

Max Act: 1.8677. Min Act: -0.0000

Data Index: 1462034 (Python Code)

Max Activating Token Index: 332

Text #10

Max Range: 2.4572. Min Range: -2.4572

Max Act: 1.8388. Min Act: -0.0000

Data Index: 1329355 (C4 (Web Text))

Max Activating Token Index: 211

Text #11

Max Range: 2.4572. Min Range: -2.4572

Max Act: 1.8125. Min Act: -0.0000

Data Index: 1179628 (C4 (Web Text))

Max Activating Token Index: 967

Text #12

Max Range: 2.4572. Min Range: -2.4572

Max Act: 1.7986. Min Act: -0.0000

Data Index: 308476 (C4 (Web Text))

Max Activating Token Index: 446

Text #13

Max Range: 2.4572. Min Range: -2.4572

Max Act: 1.8001. Min Act: -0.0000

Data Index: 1080380 (C4 (Web Text))

Max Activating Token Index: 385

Text #14

Max Range: 2.4572. Min Range: -2.4572

Max Act: 1.7810. Min Act: -0.0000

Data Index: 1613667 (Python Code)

Max Activating Token Index: 460

Text #15

Max Range: 2.4572. Min Range: -2.4572

Max Act: 1.6100. Min Act: -0.0000

Data Index: 1538773 (Python Code)

Max Activating Token Index: 198

Text #16

Max Range: 2.4572. Min Range: -2.4572

Max Act: 1.7008. Min Act: -0.0000

Data Index: 79380 (C4 (Web Text))

Max Activating Token Index: 344

Text #17

Max Range: 2.4572. Min Range: -2.4572

Max Act: 1.7753. Min Act: -0.0000

Data Index: 1539510 (Python Code)

Max Activating Token Index: 833

Text #18

Max Range: 2.4572. Min Range: -2.4572

Max Act: 1.6780. Min Act: -0.0000

Data Index: 853219 (C4 (Web Text))

Max Activating Token Index: 189

Text #19

Max Range: 2.4572. Min Range: -2.4572

Max Act: 1.6669. Min Act: -0.0000

Data Index: 183771 (C4 (Web Text))

Max Activating Token Index: 397