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

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

Neuron 3117 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: 2.0312. Min Range: -2.0312

Max Act: 2.0312. Min Act: -0.0002

Data Index: 1591088 (Python Code)

Max Activating Token Index: 32

Text #1

Max Range: 2.0312. Min Range: -2.0312

Max Act: 1.8389. Min Act: -0.0002

Data Index: 1559286 (Python Code)

Max Activating Token Index: 55

Text #2

Max Range: 2.0312. Min Range: -2.0312

Max Act: 1.7271. Min Act: -0.0002

Data Index: 1472180 (Python Code)

Max Activating Token Index: 239

Text #3

Max Range: 2.0312. Min Range: -2.0312

Max Act: 1.7155. Min Act: -0.0002

Data Index: 1629689 (Python Code)

Max Activating Token Index: 13

Text #4

Max Range: 2.0312. Min Range: -2.0312

Max Act: 1.7351. Min Act: -0.0002

Data Index: 1482782 (Python Code)

Max Activating Token Index: 157

Text #5

Max Range: 2.0312. Min Range: -2.0312

Max Act: 1.6387. Min Act: -0.0002

Data Index: 1538584 (Python Code)

Max Activating Token Index: 46

Text #6

Max Range: 2.0312. Min Range: -2.0312

Max Act: 1.6208. Min Act: -0.0002

Data Index: 1426688 (Python Code)

Max Activating Token Index: 14

Text #7

Max Range: 2.0312. Min Range: -2.0312

Max Act: 1.5629. Min Act: -0.0002

Data Index: 1581563 (Python Code)

Max Activating Token Index: 493

Text #8

Max Range: 2.0312. Min Range: -2.0312

Max Act: 1.5502. Min Act: -0.0002

Data Index: 1430457 (Python Code)

Max Activating Token Index: 53

Text #9

Max Range: 2.0312. Min Range: -2.0312

Max Act: 1.5731. Min Act: -0.0002

Data Index: 1471014 (Python Code)

Max Activating Token Index: 208

Text #10

Max Range: 2.0312. Min Range: -2.0312

Max Act: 1.4997. Min Act: -0.0002

Data Index: 1378762 (Python Code)

Max Activating Token Index: 411

Text #11

Max Range: 2.0312. Min Range: -2.0312

Max Act: 1.4721. Min Act: -0.0002

Data Index: 1511294 (Python Code)

Max Activating Token Index: 620

Text #12

Max Range: 2.0312. Min Range: -2.0312

Max Act: 1.5148. Min Act: -0.0002

Data Index: 1515814 (Python Code)

Max Activating Token Index: 750

Text #13

Max Range: 2.0312. Min Range: -2.0312

Max Act: 1.4165. Min Act: -0.0002

Data Index: 1473133 (Python Code)

Max Activating Token Index: 173

Text #14

Max Range: 2.0312. Min Range: -2.0312

Max Act: 1.4729. Min Act: -0.0002

Data Index: 1519157 (Python Code)

Max Activating Token Index: 77

Text #15

Max Range: 2.0312. Min Range: -2.0312

Max Act: 1.4418. Min Act: -0.0002

Data Index: 1476615 (Python Code)

Max Activating Token Index: 14

Text #16

Max Range: 2.0312. Min Range: -2.0312

Max Act: 1.4303. Min Act: -0.0002

Data Index: 1628933 (Python Code)

Max Activating Token Index: 367

Text #17

Max Range: 2.0312. Min Range: -2.0312

Max Act: 1.4436. Min Act: -0.0002

Data Index: 1464952 (Python Code)

Max Activating Token Index: 53

Text #18

Max Range: 2.0312. Min Range: -2.0312

Max Act: 1.4407. Min Act: -0.0002

Data Index: 1501019 (Python Code)

Max Activating Token Index: 510

Text #19

Max Range: 2.0312. Min Range: -2.0312

Max Act: 1.4234. Min Act: -0.0002

Data Index: 1467927 (Python Code)

Max Activating Token Index: 29