Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3881 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.7299. Min Range: -1.7299

Max Act: 1.7299. Min Act: -0.0000

Data Index: 1519013 (Python Code)

Max Activating Token Index: 242

Text #1

Max Range: 1.7299. Min Range: -1.7299

Max Act: 1.6425. Min Act: -0.0000

Data Index: 1559331 (Python Code)

Max Activating Token Index: 147

Text #2

Max Range: 1.7299. Min Range: -1.7299

Max Act: 1.6081. Min Act: -0.0001

Data Index: 277856 (C4 (Web Text))

Max Activating Token Index: 94

Text #3

Max Range: 1.7299. Min Range: -1.7299

Max Act: 1.5595. Min Act: -0.0000

Data Index: 1604008 (Python Code)

Max Activating Token Index: 195

Text #4

Max Range: 1.7299. Min Range: -1.7299

Max Act: 1.5397. Min Act: -0.0001

Data Index: 810204 (C4 (Web Text))

Max Activating Token Index: 94

Text #5

Max Range: 1.7299. Min Range: -1.7299

Max Act: 1.5963. Min Act: -0.0001

Data Index: 743723 (C4 (Web Text))

Max Activating Token Index: 85

Text #6

Max Range: 1.7299. Min Range: -1.7299

Max Act: 1.5592. Min Act: -0.0000

Data Index: 1005170 (C4 (Web Text))

Max Activating Token Index: 90

Text #7

Max Range: 1.7299. Min Range: -1.7299

Max Act: 1.5864. Min Act: -0.0001

Data Index: 83365 (C4 (Web Text))

Max Activating Token Index: 102

Text #8

Max Range: 1.7299. Min Range: -1.7299

Max Act: 1.4819. Min Act: -0.0000

Data Index: 1575149 (Python Code)

Max Activating Token Index: 914

Text #9

Max Range: 1.7299. Min Range: -1.7299

Max Act: 1.5654. Min Act: -0.0000

Data Index: 1630277 (Python Code)

Max Activating Token Index: 949

Text #10

Max Range: 1.7299. Min Range: -1.7299

Max Act: 1.5496. Min Act: -0.0001

Data Index: 529479 (C4 (Web Text))

Max Activating Token Index: 108

Text #11

Max Range: 1.7299. Min Range: -1.7299

Max Act: 1.4679. Min Act: -0.0000

Data Index: 1460311 (Python Code)

Max Activating Token Index: 609

Text #12

Max Range: 1.7299. Min Range: -1.7299

Max Act: 1.4852. Min Act: -0.0001

Data Index: 592021 (C4 (Web Text))

Max Activating Token Index: 325

Text #13

Max Range: 1.7299. Min Range: -1.7299

Max Act: 1.4598. Min Act: -0.0000

Data Index: 361878 (C4 (Web Text))

Max Activating Token Index: 145

Text #14

Max Range: 1.7299. Min Range: -1.7299

Max Act: 1.4158. Min Act: -0.0001

Data Index: 1340446 (C4 (Web Text))

Max Activating Token Index: 102

Text #15

Max Range: 1.7299. Min Range: -1.7299

Max Act: 1.3888. Min Act: -0.0001

Data Index: 1495574 (Python Code)

Max Activating Token Index: 993

Text #16

Max Range: 1.7299. Min Range: -1.7299

Max Act: 1.4356. Min Act: -0.0001

Data Index: 493320 (C4 (Web Text))

Max Activating Token Index: 115

Text #17

Max Range: 1.7299. Min Range: -1.7299

Max Act: 1.4306. Min Act: -0.0000

Data Index: 1548631 (Python Code)

Max Activating Token Index: 171

Text #18

Max Range: 1.7299. Min Range: -1.7299

Max Act: 1.4270. Min Act: -0.0001

Data Index: 1244202 (C4 (Web Text))

Max Activating Token Index: 145

Text #19

Max Range: 1.7299. Min Range: -1.7299

Max Act: 1.4963. Min Act: -0.0001

Data Index: 390 (C4 (Web Text))

Max Activating Token Index: 56