Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3125 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2841. Min Range: -0.2841

Max Act: 0.2841. Min Act: -0.0001

Data Index: 1410865 (Python Code)

Max Activating Token Index: 749

Text #1

Max Range: 0.2841. Min Range: -0.2841

Max Act: 0.2813. Min Act: -0.0001

Data Index: 1402691 (Python Code)

Max Activating Token Index: 724

Text #2

Max Range: 0.2841. Min Range: -0.2841

Max Act: 0.2687. Min Act: -0.0001

Data Index: 1366000 (Python Code)

Max Activating Token Index: 599

Text #3

Max Range: 0.2841. Min Range: -0.2841

Max Act: 0.2672. Min Act: -0.0001

Data Index: 1400824 (Python Code)

Max Activating Token Index: 438

Text #4

Max Range: 0.2841. Min Range: -0.2841

Max Act: 0.2537. Min Act: -0.0001

Data Index: 1536380 (Python Code)

Max Activating Token Index: 124

Text #5

Max Range: 0.2841. Min Range: -0.2841

Max Act: 0.2417. Min Act: -0.0000

Data Index: 23455 (C4 (Web Text))

Max Activating Token Index: 172

Text #6

Max Range: 0.2841. Min Range: -0.2841

Max Act: 0.2520. Min Act: -0.0001

Data Index: 1167967 (C4 (Web Text))

Max Activating Token Index: 346

Text #7

Max Range: 0.2841. Min Range: -0.2841

Max Act: 0.2410. Min Act: -0.0001

Data Index: 1359910 (Python Code)

Max Activating Token Index: 802

Text #8

Max Range: 0.2841. Min Range: -0.2841

Max Act: 0.2299. Min Act: -0.0001

Data Index: 1298795 (C4 (Web Text))

Max Activating Token Index: 181

Text #9

Max Range: 0.2841. Min Range: -0.2841

Max Act: 0.2473. Min Act: -0.0001

Data Index: 1420423 (Python Code)

Max Activating Token Index: 696

Text #10

Max Range: 0.2841. Min Range: -0.2841

Max Act: 0.2352. Min Act: -0.0001

Data Index: 1595124 (Python Code)

Max Activating Token Index: 669

Text #11

Max Range: 0.2841. Min Range: -0.2841

Max Act: 0.2277. Min Act: -0.0001

Data Index: 1655013 (Python Code)

Max Activating Token Index: 799

Text #12

Max Range: 0.2841. Min Range: -0.2841

Max Act: 0.1998. Min Act: -0.0000

Data Index: 751683 (C4 (Web Text))

Max Activating Token Index: 815

Text #13

Max Range: 0.2841. Min Range: -0.2841

Max Act: 0.2320. Min Act: -0.0001

Data Index: 1621215 (Python Code)

Max Activating Token Index: 815

Text #14

Max Range: 0.2841. Min Range: -0.2841

Max Act: 0.2226. Min Act: -0.0000

Data Index: 1393585 (Python Code)

Max Activating Token Index: 848

Text #15

Max Range: 0.2841. Min Range: -0.2841

Max Act: 0.2302. Min Act: -0.0001

Data Index: 1471483 (Python Code)

Max Activating Token Index: 771

Text #16

Max Range: 0.2841. Min Range: -0.2841

Max Act: 0.2060. Min Act: -0.0001

Data Index: 550190 (C4 (Web Text))

Max Activating Token Index: 826

Text #17

Max Range: 0.2841. Min Range: -0.2841

Max Act: 0.1963. Min Act: -0.0001

Data Index: 448735 (C4 (Web Text))

Max Activating Token Index: 124

Text #18

Max Range: 0.2841. Min Range: -0.2841

Max Act: 0.2026. Min Act: -0.0001

Data Index: 349720 (C4 (Web Text))

Max Activating Token Index: 481

Text #19

Max Range: 0.2841. Min Range: -0.2841

Max Act: 0.2109. Min Act: -0.0001

Data Index: 1578125 (Python Code)

Max Activating Token Index: 708