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

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

Neuron 3470 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: 2.2306. Min Range: -2.2306

Max Act: 2.2306. Min Act: -0.0000

Data Index: 929746 (C4 (Web Text))

Max Activating Token Index: 91

Text #1

Max Range: 2.2306. Min Range: -2.2306

Max Act: 2.2000. Min Act: -0.0000

Data Index: 761512 (C4 (Web Text))

Max Activating Token Index: 976

Text #2

Max Range: 2.2306. Min Range: -2.2306

Max Act: 1.7071. Min Act: -0.0000

Data Index: 444591 (C4 (Web Text))

Max Activating Token Index: 194

Text #3

Max Range: 2.2306. Min Range: -2.2306

Max Act: 1.9115. Min Act: -0.0000

Data Index: 117533 (C4 (Web Text))

Max Activating Token Index: 355

Text #4

Max Range: 2.2306. Min Range: -2.2306

Max Act: 1.9987. Min Act: -0.0000

Data Index: 855979 (C4 (Web Text))

Max Activating Token Index: 902

Text #5

Max Range: 2.2306. Min Range: -2.2306

Max Act: 2.0944. Min Act: -0.0001

Data Index: 1301043 (C4 (Web Text))

Max Activating Token Index: 664

Text #6

Max Range: 2.2306. Min Range: -2.2306

Max Act: 2.1761. Min Act: -0.0000

Data Index: 439927 (C4 (Web Text))

Max Activating Token Index: 359

Text #7

Max Range: 2.2306. Min Range: -2.2306

Max Act: 1.9763. Min Act: -0.0000

Data Index: 11185 (C4 (Web Text))

Max Activating Token Index: 397

Text #8

Max Range: 2.2306. Min Range: -2.2306

Max Act: 1.8553. Min Act: -0.0000

Data Index: 1120916 (C4 (Web Text))

Max Activating Token Index: 340

Text #9

Max Range: 2.2306. Min Range: -2.2306

Max Act: 2.1099. Min Act: -0.0000

Data Index: 1063472 (C4 (Web Text))

Max Activating Token Index: 923

Text #10

Max Range: 2.2306. Min Range: -2.2306

Max Act: 2.1140. Min Act: -0.0000

Data Index: 783832 (C4 (Web Text))

Max Activating Token Index: 296

Text #11

Max Range: 2.2306. Min Range: -2.2306

Max Act: 1.8760. Min Act: -0.0000

Data Index: 193951 (C4 (Web Text))

Max Activating Token Index: 250

Text #12

Max Range: 2.2306. Min Range: -2.2306

Max Act: 1.9822. Min Act: -0.0001

Data Index: 794457 (C4 (Web Text))

Max Activating Token Index: 626

Text #13

Max Range: 2.2306. Min Range: -2.2306

Max Act: 2.0677. Min Act: -0.0000

Data Index: 1046755 (C4 (Web Text))

Max Activating Token Index: 92

Text #14

Max Range: 2.2306. Min Range: -2.2306

Max Act: 1.8593. Min Act: -0.0001

Data Index: 1088595 (C4 (Web Text))

Max Activating Token Index: 194

Text #15

Max Range: 2.2306. Min Range: -2.2306

Max Act: 1.9736. Min Act: -0.0001

Data Index: 72381 (C4 (Web Text))

Max Activating Token Index: 729

Text #16

Max Range: 2.2306. Min Range: -2.2306

Max Act: 1.8354. Min Act: -0.0000

Data Index: 76355 (C4 (Web Text))

Max Activating Token Index: 717

Text #17

Max Range: 2.2306. Min Range: -2.2306

Max Act: 1.7268. Min Act: -0.0000

Data Index: 342025 (C4 (Web Text))

Max Activating Token Index: 731

Text #18

Max Range: 2.2306. Min Range: -2.2306

Max Act: 1.9140. Min Act: -0.0001

Data Index: 958838 (C4 (Web Text))

Max Activating Token Index: 499

Text #19

Max Range: 2.2306. Min Range: -2.2306

Max Act: 2.0128. Min Act: -0.0001

Data Index: 569821 (C4 (Web Text))

Max Activating Token Index: 860