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

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

Neuron 5897 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: 7.5845. Min Range: -7.5845

Max Act: 7.5845. Min Act: -0.0000

Data Index: 252072 (C4 (Web Text))

Max Activating Token Index: 101

Text #1

Max Range: 7.5845. Min Range: -7.5845

Max Act: 5.1896. Min Act: -0.0000

Data Index: 407058 (C4 (Web Text))

Max Activating Token Index: 1021

Text #2

Max Range: 7.5845. Min Range: -7.5845

Max Act: 4.5521. Min Act: -0.0000

Data Index: 965457 (C4 (Web Text))

Max Activating Token Index: 830

Text #3

Max Range: 7.5845. Min Range: -7.5845

Max Act: 4.2685. Min Act: -0.0000

Data Index: 557262 (C4 (Web Text))

Max Activating Token Index: 405

Text #4

Max Range: 7.5845. Min Range: -7.5845

Max Act: 4.0241. Min Act: -0.0000

Data Index: 932024 (C4 (Web Text))

Max Activating Token Index: 610

Text #5

Max Range: 7.5845. Min Range: -7.5845

Max Act: 3.7948. Min Act: -0.0000

Data Index: 1004763 (C4 (Web Text))

Max Activating Token Index: 320

Text #6

Max Range: 7.5845. Min Range: -7.5845

Max Act: 4.1620. Min Act: -0.0000

Data Index: 1228297 (C4 (Web Text))

Max Activating Token Index: 450

Text #7

Max Range: 7.5845. Min Range: -7.5845

Max Act: 3.7164. Min Act: -0.0000

Data Index: 577030 (C4 (Web Text))

Max Activating Token Index: 240

Text #8

Max Range: 7.5845. Min Range: -7.5845

Max Act: 3.9907. Min Act: -0.0000

Data Index: 89068 (C4 (Web Text))

Max Activating Token Index: 557

Text #9

Max Range: 7.5845. Min Range: -7.5845

Max Act: 3.2830. Min Act: -0.0000

Data Index: 1239143 (C4 (Web Text))

Max Activating Token Index: 1014

Text #10

Max Range: 7.5845. Min Range: -7.5845

Max Act: 3.7557. Min Act: -0.0000

Data Index: 193289 (C4 (Web Text))

Max Activating Token Index: 862

Text #11

Max Range: 7.5845. Min Range: -7.5845

Max Act: 3.6383. Min Act: -0.0000

Data Index: 52462 (C4 (Web Text))

Max Activating Token Index: 601

Text #12

Max Range: 7.5845. Min Range: -7.5845

Max Act: 2.8812. Min Act: -0.0000

Data Index: 1537810 (Python Code)

Max Activating Token Index: 272

Text #13

Max Range: 7.5845. Min Range: -7.5845

Max Act: 2.7575. Min Act: -0.0000

Data Index: 589935 (C4 (Web Text))

Max Activating Token Index: 958

Text #14

Max Range: 7.5845. Min Range: -7.5845

Max Act: 2.2939. Min Act: -0.0000

Data Index: 1530466 (Python Code)

Max Activating Token Index: 255

Text #15

Max Range: 7.5845. Min Range: -7.5845

Max Act: 2.3485. Min Act: -0.0000

Data Index: 1429196 (Python Code)

Max Activating Token Index: 179

Text #16

Max Range: 7.5845. Min Range: -7.5845

Max Act: 2.0244. Min Act: -0.0000

Data Index: 1297454 (C4 (Web Text))

Max Activating Token Index: 173

Text #17

Max Range: 7.5845. Min Range: -7.5845

Max Act: 2.3127. Min Act: -0.0000

Data Index: 750083 (C4 (Web Text))

Max Activating Token Index: 648

Text #18

Max Range: 7.5845. Min Range: -7.5845

Max Act: 2.5317. Min Act: -0.0000

Data Index: 1606693 (Python Code)

Max Activating Token Index: 869

Text #19

Max Range: 7.5845. Min Range: -7.5845

Max Act: 2.1255. Min Act: -0.0000

Data Index: 1522596 (Python Code)

Max Activating Token Index: 486