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

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

Neuron 490 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: 0.5843. Min Range: -0.5843

Max Act: 0.5843. Min Act: -0.0001

Data Index: 1541921 (Python Code)

Max Activating Token Index: 468

Text #1

Max Range: 0.5843. Min Range: -0.5843

Max Act: 0.5447. Min Act: -0.0001

Data Index: 1477437 (Python Code)

Max Activating Token Index: 457

Text #2

Max Range: 0.5843. Min Range: -0.5843

Max Act: 0.5268. Min Act: -0.0001

Data Index: 1513431 (Python Code)

Max Activating Token Index: 503

Text #3

Max Range: 0.5843. Min Range: -0.5843

Max Act: 0.4894. Min Act: -0.0001

Data Index: 1622326 (Python Code)

Max Activating Token Index: 636

Text #4

Max Range: 0.5843. Min Range: -0.5843

Max Act: 0.5081. Min Act: -0.0001

Data Index: 1416828 (Python Code)

Max Activating Token Index: 995

Text #5

Max Range: 0.5843. Min Range: -0.5843

Max Act: 0.5065. Min Act: -0.0001

Data Index: 1623606 (Python Code)

Max Activating Token Index: 555

Text #6

Max Range: 0.5843. Min Range: -0.5843

Max Act: 0.4146. Min Act: -0.0001

Data Index: 1402821 (Python Code)

Max Activating Token Index: 769

Text #7

Max Range: 0.5843. Min Range: -0.5843

Max Act: 0.4769. Min Act: -0.0001

Data Index: 1389430 (Python Code)

Max Activating Token Index: 823

Text #8

Max Range: 0.5843. Min Range: -0.5843

Max Act: 0.4279. Min Act: -0.0001

Data Index: 1473583 (Python Code)

Max Activating Token Index: 764

Text #9

Max Range: 0.5843. Min Range: -0.5843

Max Act: 0.4643. Min Act: -0.0001

Data Index: 1647211 (Python Code)

Max Activating Token Index: 378

Text #10

Max Range: 0.5843. Min Range: -0.5843

Max Act: 0.4465. Min Act: -0.0001

Data Index: 1473110 (Python Code)

Max Activating Token Index: 536

Text #11

Max Range: 0.5843. Min Range: -0.5843

Max Act: 0.4424. Min Act: -0.0001

Data Index: 1493581 (Python Code)

Max Activating Token Index: 535

Text #12

Max Range: 0.5843. Min Range: -0.5843

Max Act: 0.4316. Min Act: -0.0000

Data Index: 903366 (C4 (Web Text))

Max Activating Token Index: 774

Text #13

Max Range: 0.5843. Min Range: -0.5843

Max Act: 0.4253. Min Act: -0.0001

Data Index: 1550056 (Python Code)

Max Activating Token Index: 400

Text #14

Max Range: 0.5843. Min Range: -0.5843

Max Act: 0.4367. Min Act: -0.0001

Data Index: 1472451 (Python Code)

Max Activating Token Index: 30

Text #15

Max Range: 0.5843. Min Range: -0.5843

Max Act: 0.4960. Min Act: -0.0001

Data Index: 1498300 (Python Code)

Max Activating Token Index: 484

Text #16

Max Range: 0.5843. Min Range: -0.5843

Max Act: 0.4240. Min Act: -0.0001

Data Index: 1584935 (Python Code)

Max Activating Token Index: 825

Text #17

Max Range: 0.5843. Min Range: -0.5843

Max Act: 0.4155. Min Act: -0.0001

Data Index: 1396434 (Python Code)

Max Activating Token Index: 605

Text #18

Max Range: 0.5843. Min Range: -0.5843

Max Act: 0.4149. Min Act: -0.0001

Data Index: 1395145 (Python Code)

Max Activating Token Index: 462

Text #19

Max Range: 0.5843. Min Range: -0.5843

Max Act: 0.4288. Min Act: -0.0001

Data Index: 1591120 (Python Code)

Max Activating Token Index: 758