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

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

Neuron 1234 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.4921. Min Act: -0.0001

Data Index: 1464106 (Python Code)

Max Activating Token Index: 816

Text #1

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.4610. Min Act: -0.0001

Data Index: 1374573 (Python Code)

Max Activating Token Index: 794

Text #2

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.4765. Min Act: -0.0000

Data Index: 343241 (C4 (Web Text))

Max Activating Token Index: 816

Text #3

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.4703. Min Act: -0.0001

Data Index: 1598345 (Python Code)

Max Activating Token Index: 238

Text #4

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.4666. Min Act: -0.0001

Data Index: 827941 (C4 (Web Text))

Max Activating Token Index: 99

Text #5

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.4527. Min Act: -0.0001

Data Index: 774779 (C4 (Web Text))

Max Activating Token Index: 841

Text #6

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.4372. Min Act: -0.0001

Data Index: 1586447 (Python Code)

Max Activating Token Index: 969

Text #7

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.4486. Min Act: -0.0001

Data Index: 1430220 (Python Code)

Max Activating Token Index: 86

Text #8

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.4593. Min Act: -0.0000

Data Index: 700832 (C4 (Web Text))

Max Activating Token Index: 629

Text #9

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.4339. Min Act: -0.0001

Data Index: 1388121 (Python Code)

Max Activating Token Index: 680

Text #10

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.4306. Min Act: -0.0001

Data Index: 137470 (C4 (Web Text))

Max Activating Token Index: 694

Text #11

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.4203. Min Act: -0.0001

Data Index: 1172022 (C4 (Web Text))

Max Activating Token Index: 332

Text #12

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.4185. Min Act: -0.0001

Data Index: 415356 (C4 (Web Text))

Max Activating Token Index: 605

Text #13

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.4170. Min Act: -0.0001

Data Index: 1442913 (Python Code)

Max Activating Token Index: 57

Text #14

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.4092. Min Act: -0.0001

Data Index: 864295 (C4 (Web Text))

Max Activating Token Index: 730

Text #15

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.4154. Min Act: -0.0001

Data Index: 292022 (C4 (Web Text))

Max Activating Token Index: 626

Text #16

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.4232. Min Act: -0.0000

Data Index: 253544 (C4 (Web Text))

Max Activating Token Index: 335

Text #17

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.4095. Min Act: -0.0000

Data Index: 836382 (C4 (Web Text))

Max Activating Token Index: 199

Text #18

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3969. Min Act: -0.0001

Data Index: 1647147 (Python Code)

Max Activating Token Index: 586

Text #19

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.4031. Min Act: -0.0000

Data Index: 812004 (C4 (Web Text))

Max Activating Token Index: 755