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

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

Neuron 2394 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0371. Min Act: -0.0002

Data Index: 1447399 (Python Code)

Max Activating Token Index: 5

Text #1

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0368. Min Act: -0.0002

Data Index: 1396976 (Python Code)

Max Activating Token Index: 8

Text #2

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0344. Min Act: -0.0002

Data Index: 1475692 (Python Code)

Max Activating Token Index: 5

Text #3

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0338. Min Act: -0.0002

Data Index: 1609873 (Python Code)

Max Activating Token Index: 4

Text #4

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0334. Min Act: -0.0002

Data Index: 1378283 (Python Code)

Max Activating Token Index: 7

Text #5

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0323. Min Act: -0.0003

Data Index: 499962 (C4 (Web Text))

Max Activating Token Index: 5

Text #6

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0321. Min Act: -0.0002

Data Index: 1609856 (Python Code)

Max Activating Token Index: 7

Text #7

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0312. Min Act: -0.0002

Data Index: 1544501 (Python Code)

Max Activating Token Index: 6

Text #8

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0301. Min Act: -0.0002

Data Index: 1369356 (Python Code)

Max Activating Token Index: 10

Text #9

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0304. Min Act: -0.0002

Data Index: 1554850 (Python Code)

Max Activating Token Index: 6

Text #10

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0301. Min Act: -0.0002

Data Index: 1536396 (Python Code)

Max Activating Token Index: 5

Text #11

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0297. Min Act: -0.0002

Data Index: 1617856 (Python Code)

Max Activating Token Index: 5

Text #12

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0296. Min Act: -0.0003

Data Index: 1304571 (C4 (Web Text))

Max Activating Token Index: 6

Text #13

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0294. Min Act: -0.0002

Data Index: 1481939 (Python Code)

Max Activating Token Index: 7

Text #14

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0293. Min Act: -0.0002

Data Index: 1490624 (Python Code)

Max Activating Token Index: 4

Text #15

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0292. Min Act: -0.0002

Data Index: 1458095 (Python Code)

Max Activating Token Index: 7

Text #16

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0291. Min Act: -0.0002

Data Index: 1609935 (Python Code)

Max Activating Token Index: 5

Text #17

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0289. Min Act: -0.0002

Data Index: 1543606 (Python Code)

Max Activating Token Index: 4

Text #18

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0287. Min Act: -0.0002

Data Index: 1546198 (Python Code)

Max Activating Token Index: 4

Text #19

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0287. Min Act: -0.0002

Data Index: 1536134 (Python Code)

Max Activating Token Index: 8