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

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

Neuron 4419 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.2697. Min Act: -0.0002

Data Index: 1377781 (Python Code)

Max Activating Token Index: 928

Text #1

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.2629. Min Act: -0.0002

Data Index: 202075 (C4 (Web Text))

Max Activating Token Index: 2

Text #2

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.2629. Min Act: -0.0002

Data Index: 136250 (C4 (Web Text))

Max Activating Token Index: 2

Text #3

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.2673. Min Act: -0.0002

Data Index: 1561575 (Python Code)

Max Activating Token Index: 944

Text #4

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.2517. Min Act: -0.0002

Data Index: 1466784 (Python Code)

Max Activating Token Index: 77

Text #5

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.2460. Min Act: -0.0002

Data Index: 1434492 (Python Code)

Max Activating Token Index: 31

Text #6

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.2420. Min Act: -0.0002

Data Index: 1428678 (Python Code)

Max Activating Token Index: 3

Text #7

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.2440. Min Act: -0.0002

Data Index: 295606 (C4 (Web Text))

Max Activating Token Index: 146

Text #8

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.2402. Min Act: -0.0002

Data Index: 1421761 (Python Code)

Max Activating Token Index: 973

Text #9

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.2377. Min Act: -0.0002

Data Index: 1552490 (Python Code)

Max Activating Token Index: 116

Text #10

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.2314. Min Act: -0.0002

Data Index: 677945 (C4 (Web Text))

Max Activating Token Index: 126

Text #11

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.2341. Min Act: -0.0002

Data Index: 602473 (C4 (Web Text))

Max Activating Token Index: 4

Text #12

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.2351. Min Act: -0.0002

Data Index: 579289 (C4 (Web Text))

Max Activating Token Index: 666

Text #13

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.2347. Min Act: -0.0002

Data Index: 1513905 (Python Code)

Max Activating Token Index: 141

Text #14

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.2290. Min Act: -0.0002

Data Index: 1592425 (Python Code)

Max Activating Token Index: 18

Text #15

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.2244. Min Act: -0.0002

Data Index: 1369550 (Python Code)

Max Activating Token Index: 951

Text #16

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.2211. Min Act: -0.0002

Data Index: 1362679 (Python Code)

Max Activating Token Index: 10

Text #17

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.2234. Min Act: -0.0002

Data Index: 1433731 (Python Code)

Max Activating Token Index: 239

Text #18

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.2207. Min Act: -0.0002

Data Index: 1367785 (Python Code)

Max Activating Token Index: 194

Text #19

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.2202. Min Act: -0.0002

Data Index: 1638873 (Python Code)

Max Activating Token Index: 259