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

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

Neuron 1930 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0250. Min Range: -5.0250

Max Act: 5.0250. Min Act: -0.0000

Data Index: 765419 (C4 (Web Text))

Max Activating Token Index: 988

Text #1

Max Range: 5.0250. Min Range: -5.0250

Max Act: 3.4341. Min Act: -0.0001

Data Index: 753638 (C4 (Web Text))

Max Activating Token Index: 950

Text #2

Max Range: 5.0250. Min Range: -5.0250

Max Act: 3.4927. Min Act: -0.0001

Data Index: 1289401 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 5.0250. Min Range: -5.0250

Max Act: 3.4119. Min Act: -0.0001

Data Index: 925046 (C4 (Web Text))

Max Activating Token Index: 210

Text #4

Max Range: 5.0250. Min Range: -5.0250

Max Act: 3.3749. Min Act: -0.0001

Data Index: 858214 (C4 (Web Text))

Max Activating Token Index: 646

Text #5

Max Range: 5.0250. Min Range: -5.0250

Max Act: 3.1397. Min Act: -0.0001

Data Index: 100362 (C4 (Web Text))

Max Activating Token Index: 335

Text #6

Max Range: 5.0250. Min Range: -5.0250

Max Act: 3.2491. Min Act: -0.0001

Data Index: 799870 (C4 (Web Text))

Max Activating Token Index: 150

Text #7

Max Range: 5.0250. Min Range: -5.0250

Max Act: 3.0992. Min Act: -0.0000

Data Index: 920462 (C4 (Web Text))

Max Activating Token Index: 40

Text #8

Max Range: 5.0250. Min Range: -5.0250

Max Act: 3.1328. Min Act: -0.0001

Data Index: 89979 (C4 (Web Text))

Max Activating Token Index: 895

Text #9

Max Range: 5.0250. Min Range: -5.0250

Max Act: 3.1647. Min Act: -0.0000

Data Index: 1179819 (C4 (Web Text))

Max Activating Token Index: 15

Text #10

Max Range: 5.0250. Min Range: -5.0250

Max Act: 3.1280. Min Act: -0.0001

Data Index: 1175353 (C4 (Web Text))

Max Activating Token Index: 669

Text #11

Max Range: 5.0250. Min Range: -5.0250

Max Act: 3.2325. Min Act: -0.0000

Data Index: 131080 (C4 (Web Text))

Max Activating Token Index: 236

Text #12

Max Range: 5.0250. Min Range: -5.0250

Max Act: 3.2086. Min Act: -0.0001

Data Index: 459773 (C4 (Web Text))

Max Activating Token Index: 41

Text #13

Max Range: 5.0250. Min Range: -5.0250

Max Act: 3.2327. Min Act: -0.0001

Data Index: 591457 (C4 (Web Text))

Max Activating Token Index: 226

Text #14

Max Range: 5.0250. Min Range: -5.0250

Max Act: 2.8779. Min Act: -0.0000

Data Index: 1537581 (Python Code)

Max Activating Token Index: 30

Text #15

Max Range: 5.0250. Min Range: -5.0250

Max Act: 2.9608. Min Act: -0.0001

Data Index: 394258 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 5.0250. Min Range: -5.0250

Max Act: 2.8992. Min Act: -0.0001

Data Index: 454967 (C4 (Web Text))

Max Activating Token Index: 628

Text #17

Max Range: 5.0250. Min Range: -5.0250

Max Act: 2.9124. Min Act: -0.0001

Data Index: 1311674 (C4 (Web Text))

Max Activating Token Index: 57

Text #18

Max Range: 5.0250. Min Range: -5.0250

Max Act: 2.9094. Min Act: -0.0001

Data Index: 838274 (C4 (Web Text))

Max Activating Token Index: 449

Text #19

Max Range: 5.0250. Min Range: -5.0250

Max Act: 2.8781. Min Act: -0.0001

Data Index: 499881 (C4 (Web Text))

Max Activating Token Index: 446