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

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

Neuron 5629 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4230. Min Range: -3.4230

Max Act: 3.4230. Min Act: -0.0000

Data Index: 1306287 (C4 (Web Text))

Max Activating Token Index: 842

Text #1

Max Range: 3.4230. Min Range: -3.4230

Max Act: 3.2428. Min Act: -0.0000

Data Index: 564253 (C4 (Web Text))

Max Activating Token Index: 923

Text #2

Max Range: 3.4230. Min Range: -3.4230

Max Act: 3.0145. Min Act: -0.0000

Data Index: 1528456 (Python Code)

Max Activating Token Index: 344

Text #3

Max Range: 3.4230. Min Range: -3.4230

Max Act: 3.1159. Min Act: -0.0000

Data Index: 1301386 (C4 (Web Text))

Max Activating Token Index: 918

Text #4

Max Range: 3.4230. Min Range: -3.4230

Max Act: 3.2095. Min Act: -0.0000

Data Index: 800574 (C4 (Web Text))

Max Activating Token Index: 815

Text #5

Max Range: 3.4230. Min Range: -3.4230

Max Act: 3.0310. Min Act: -0.0000

Data Index: 539296 (C4 (Web Text))

Max Activating Token Index: 612

Text #6

Max Range: 3.4230. Min Range: -3.4230

Max Act: 3.1004. Min Act: -0.0000

Data Index: 975558 (C4 (Web Text))

Max Activating Token Index: 153

Text #7

Max Range: 3.4230. Min Range: -3.4230

Max Act: 3.0522. Min Act: -0.0000

Data Index: 375262 (C4 (Web Text))

Max Activating Token Index: 176

Text #8

Max Range: 3.4230. Min Range: -3.4230

Max Act: 2.7637. Min Act: -0.0000

Data Index: 933286 (C4 (Web Text))

Max Activating Token Index: 938

Text #9

Max Range: 3.4230. Min Range: -3.4230

Max Act: 2.8763. Min Act: -0.0000

Data Index: 403465 (C4 (Web Text))

Max Activating Token Index: 416

Text #10

Max Range: 3.4230. Min Range: -3.4230

Max Act: 2.7091. Min Act: -0.0000

Data Index: 1131761 (C4 (Web Text))

Max Activating Token Index: 66

Text #11

Max Range: 3.4230. Min Range: -3.4230

Max Act: 2.8390. Min Act: -0.0000

Data Index: 838821 (C4 (Web Text))

Max Activating Token Index: 516

Text #12

Max Range: 3.4230. Min Range: -3.4230

Max Act: 2.6996. Min Act: -0.0000

Data Index: 1217140 (C4 (Web Text))

Max Activating Token Index: 803

Text #13

Max Range: 3.4230. Min Range: -3.4230

Max Act: 2.6605. Min Act: -0.0000

Data Index: 1086211 (C4 (Web Text))

Max Activating Token Index: 944

Text #14

Max Range: 3.4230. Min Range: -3.4230

Max Act: 2.7525. Min Act: -0.0000

Data Index: 12754 (C4 (Web Text))

Max Activating Token Index: 747

Text #15

Max Range: 3.4230. Min Range: -3.4230

Max Act: 2.6169. Min Act: -0.0000

Data Index: 1096671 (C4 (Web Text))

Max Activating Token Index: 430

Text #16

Max Range: 3.4230. Min Range: -3.4230

Max Act: 2.5769. Min Act: -0.0000

Data Index: 823788 (C4 (Web Text))

Max Activating Token Index: 652

Text #17

Max Range: 3.4230. Min Range: -3.4230

Max Act: 2.5745. Min Act: -0.0000

Data Index: 1656259 (Python Code)

Max Activating Token Index: 199

Text #18

Max Range: 3.4230. Min Range: -3.4230

Max Act: 2.5086. Min Act: -0.0000

Data Index: 718176 (C4 (Web Text))

Max Activating Token Index: 255

Text #19

Max Range: 3.4230. Min Range: -3.4230

Max Act: 2.4582. Min Act: -0.0000

Data Index: 328990 (C4 (Web Text))

Max Activating Token Index: 539