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

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

Neuron 4049 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7158. Min Range: -1.7158

Max Act: 1.5786. Min Act: -0.0001

Data Index: 1568863 (Python Code)

Max Activating Token Index: 242

Text #1

Max Range: 1.7158. Min Range: -1.7158

Max Act: 1.7046. Min Act: -0.0001

Data Index: 1605401 (Python Code)

Max Activating Token Index: 295

Text #2

Max Range: 1.7158. Min Range: -1.7158

Max Act: 1.7158. Min Act: -0.0001

Data Index: 1620880 (Python Code)

Max Activating Token Index: 288

Text #3

Max Range: 1.7158. Min Range: -1.7158

Max Act: 1.6290. Min Act: -0.0001

Data Index: 1367295 (Python Code)

Max Activating Token Index: 259

Text #4

Max Range: 1.7158. Min Range: -1.7158

Max Act: 1.6205. Min Act: -0.0001

Data Index: 1545356 (Python Code)

Max Activating Token Index: 229

Text #5

Max Range: 1.7158. Min Range: -1.7158

Max Act: 1.5036. Min Act: -0.0001

Data Index: 1447247 (Python Code)

Max Activating Token Index: 504

Text #6

Max Range: 1.7158. Min Range: -1.7158

Max Act: 1.4945. Min Act: -0.0001

Data Index: 1635380 (Python Code)

Max Activating Token Index: 407

Text #7

Max Range: 1.7158. Min Range: -1.7158

Max Act: 1.4544. Min Act: -0.0001

Data Index: 1494049 (Python Code)

Max Activating Token Index: 384

Text #8

Max Range: 1.7158. Min Range: -1.7158

Max Act: 1.4253. Min Act: -0.0001

Data Index: 1419221 (Python Code)

Max Activating Token Index: 492

Text #9

Max Range: 1.7158. Min Range: -1.7158

Max Act: 1.5433. Min Act: -0.0001

Data Index: 1548390 (Python Code)

Max Activating Token Index: 375

Text #10

Max Range: 1.7158. Min Range: -1.7158

Max Act: 1.5075. Min Act: -0.0001

Data Index: 1502241 (Python Code)

Max Activating Token Index: 512

Text #11

Max Range: 1.7158. Min Range: -1.7158

Max Act: 1.4124. Min Act: -0.0001

Data Index: 1431534 (Python Code)

Max Activating Token Index: 119

Text #12

Max Range: 1.7158. Min Range: -1.7158

Max Act: 1.3082. Min Act: -0.0001

Data Index: 1607168 (Python Code)

Max Activating Token Index: 565

Text #13

Max Range: 1.7158. Min Range: -1.7158

Max Act: 1.4195. Min Act: -0.0001

Data Index: 1564594 (Python Code)

Max Activating Token Index: 442

Text #14

Max Range: 1.7158. Min Range: -1.7158

Max Act: 1.2751. Min Act: -0.0001

Data Index: 1466526 (Python Code)

Max Activating Token Index: 679

Text #15

Max Range: 1.7158. Min Range: -1.7158

Max Act: 1.3338. Min Act: -0.0001

Data Index: 1528514 (Python Code)

Max Activating Token Index: 168

Text #16

Max Range: 1.7158. Min Range: -1.7158

Max Act: 1.2070. Min Act: -0.0001

Data Index: 1632677 (Python Code)

Max Activating Token Index: 252

Text #17

Max Range: 1.7158. Min Range: -1.7158

Max Act: 1.2777. Min Act: -0.0001

Data Index: 1447136 (Python Code)

Max Activating Token Index: 687

Text #18

Max Range: 1.7158. Min Range: -1.7158

Max Act: 1.3908. Min Act: -0.0001

Data Index: 1577295 (Python Code)

Max Activating Token Index: 644

Text #19

Max Range: 1.7158. Min Range: -1.7158

Max Act: 1.2192. Min Act: -0.0001

Data Index: 1611749 (Python Code)

Max Activating Token Index: 375