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

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

Neuron 4378 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0337. Min Range: -5.0337

Max Act: 5.0337. Min Act: -0.0000

Data Index: 58743 (C4 (Web Text))

Max Activating Token Index: 51

Text #1

Max Range: 5.0337. Min Range: -5.0337

Max Act: 4.3453. Min Act: -0.0000

Data Index: 166436 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 5.0337. Min Range: -5.0337

Max Act: 4.0461. Min Act: -0.0000

Data Index: 656565 (C4 (Web Text))

Max Activating Token Index: 882

Text #3

Max Range: 5.0337. Min Range: -5.0337

Max Act: 4.5492. Min Act: -0.0000

Data Index: 1182025 (C4 (Web Text))

Max Activating Token Index: 55

Text #4

Max Range: 5.0337. Min Range: -5.0337

Max Act: 4.4194. Min Act: -0.0000

Data Index: 836449 (C4 (Web Text))

Max Activating Token Index: 56

Text #5

Max Range: 5.0337. Min Range: -5.0337

Max Act: 4.0588. Min Act: -0.0000

Data Index: 258694 (C4 (Web Text))

Max Activating Token Index: 161

Text #6

Max Range: 5.0337. Min Range: -5.0337

Max Act: 4.3831. Min Act: -0.0000

Data Index: 52356 (C4 (Web Text))

Max Activating Token Index: 722

Text #7

Max Range: 5.0337. Min Range: -5.0337

Max Act: 4.0053. Min Act: -0.0000

Data Index: 112804 (C4 (Web Text))

Max Activating Token Index: 17

Text #8

Max Range: 5.0337. Min Range: -5.0337

Max Act: 3.9401. Min Act: -0.0000

Data Index: 458816 (C4 (Web Text))

Max Activating Token Index: 30

Text #9

Max Range: 5.0337. Min Range: -5.0337

Max Act: 3.5282. Min Act: -0.0000

Data Index: 978941 (C4 (Web Text))

Max Activating Token Index: 375

Text #10

Max Range: 5.0337. Min Range: -5.0337

Max Act: 3.6957. Min Act: -0.0000

Data Index: 898380 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 5.0337. Min Range: -5.0337

Max Act: 3.7505. Min Act: -0.0000

Data Index: 1147094 (C4 (Web Text))

Max Activating Token Index: 98

Text #12

Max Range: 5.0337. Min Range: -5.0337

Max Act: 3.4693. Min Act: -0.0000

Data Index: 517824 (C4 (Web Text))

Max Activating Token Index: 157

Text #13

Max Range: 5.0337. Min Range: -5.0337

Max Act: 3.5809. Min Act: -0.0000

Data Index: 619104 (C4 (Web Text))

Max Activating Token Index: 813

Text #14

Max Range: 5.0337. Min Range: -5.0337

Max Act: 3.3531. Min Act: -0.0000

Data Index: 618434 (C4 (Web Text))

Max Activating Token Index: 169

Text #15

Max Range: 5.0337. Min Range: -5.0337

Max Act: 3.3156. Min Act: -0.0000

Data Index: 817517 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 5.0337. Min Range: -5.0337

Max Act: 3.1584. Min Act: -0.0000

Data Index: 502888 (C4 (Web Text))

Max Activating Token Index: 966

Text #17

Max Range: 5.0337. Min Range: -5.0337

Max Act: 3.3010. Min Act: -0.0000

Data Index: 1184440 (C4 (Web Text))

Max Activating Token Index: 772

Text #18

Max Range: 5.0337. Min Range: -5.0337

Max Act: 3.5962. Min Act: -0.0000

Data Index: 1242368 (C4 (Web Text))

Max Activating Token Index: 548

Text #19

Max Range: 5.0337. Min Range: -5.0337

Max Act: 3.4240. Min Act: -0.0000

Data Index: 255825 (C4 (Web Text))

Max Activating Token Index: 944