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

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

Neuron 2497 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2522. Min Range: -5.2522

Max Act: 5.2522. Min Act: -0.0001

Data Index: 64603 (C4 (Web Text))

Max Activating Token Index: 60

Text #1

Max Range: 5.2522. Min Range: -5.2522

Max Act: 4.7348. Min Act: -0.0000

Data Index: 1030156 (C4 (Web Text))

Max Activating Token Index: 609

Text #2

Max Range: 5.2522. Min Range: -5.2522

Max Act: 4.7913. Min Act: -0.0001

Data Index: 991817 (C4 (Web Text))

Max Activating Token Index: 944

Text #3

Max Range: 5.2522. Min Range: -5.2522

Max Act: 5.0651. Min Act: -0.0000

Data Index: 205349 (C4 (Web Text))

Max Activating Token Index: 372

Text #4

Max Range: 5.2522. Min Range: -5.2522

Max Act: 5.0548. Min Act: -0.0000

Data Index: 645448 (C4 (Web Text))

Max Activating Token Index: 289

Text #5

Max Range: 5.2522. Min Range: -5.2522

Max Act: 4.5136. Min Act: -0.0001

Data Index: 620912 (C4 (Web Text))

Max Activating Token Index: 713

Text #6

Max Range: 5.2522. Min Range: -5.2522

Max Act: 4.1169. Min Act: -0.0001

Data Index: 732499 (C4 (Web Text))

Max Activating Token Index: 338

Text #7

Max Range: 5.2522. Min Range: -5.2522

Max Act: 4.5744. Min Act: -0.0000

Data Index: 892434 (C4 (Web Text))

Max Activating Token Index: 860

Text #8

Max Range: 5.2522. Min Range: -5.2522

Max Act: 4.5689. Min Act: -0.0001

Data Index: 1322493 (C4 (Web Text))

Max Activating Token Index: 654

Text #9

Max Range: 5.2522. Min Range: -5.2522

Max Act: 4.3818. Min Act: -0.0000

Data Index: 1005051 (C4 (Web Text))

Max Activating Token Index: 284

Text #10

Max Range: 5.2522. Min Range: -5.2522

Max Act: 4.7107. Min Act: -0.0001

Data Index: 1088045 (C4 (Web Text))

Max Activating Token Index: 565

Text #11

Max Range: 5.2522. Min Range: -5.2522

Max Act: 4.5289. Min Act: -0.0001

Data Index: 322201 (C4 (Web Text))

Max Activating Token Index: 433

Text #12

Max Range: 5.2522. Min Range: -5.2522

Max Act: 4.3007. Min Act: -0.0000

Data Index: 160209 (C4 (Web Text))

Max Activating Token Index: 593

Text #13

Max Range: 5.2522. Min Range: -5.2522

Max Act: 4.4026. Min Act: -0.0000

Data Index: 933248 (C4 (Web Text))

Max Activating Token Index: 815

Text #14

Max Range: 5.2522. Min Range: -5.2522

Max Act: 4.0313. Min Act: -0.0000

Data Index: 698647 (C4 (Web Text))

Max Activating Token Index: 100

Text #15

Max Range: 5.2522. Min Range: -5.2522

Max Act: 4.0417. Min Act: -0.0001

Data Index: 775256 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 5.2522. Min Range: -5.2522

Max Act: 3.9906. Min Act: -0.0000

Data Index: 593213 (C4 (Web Text))

Max Activating Token Index: 465

Text #17

Max Range: 5.2522. Min Range: -5.2522

Max Act: 4.1182. Min Act: -0.0001

Data Index: 353949 (C4 (Web Text))

Max Activating Token Index: 273

Text #18

Max Range: 5.2522. Min Range: -5.2522

Max Act: 3.9326. Min Act: -0.0001

Data Index: 980873 (C4 (Web Text))

Max Activating Token Index: 901

Text #19

Max Range: 5.2522. Min Range: -5.2522

Max Act: 4.0761. Min Act: -0.0001

Data Index: 1323900 (C4 (Web Text))

Max Activating Token Index: 994