Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2307 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0387. Min Act: -0.0001

Data Index: 427526 (C4 (Web Text))

Max Activating Token Index: 937

Text #1

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0325. Min Act: -0.0001

Data Index: 263049 (C4 (Web Text))

Max Activating Token Index: 6

Text #2

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0295. Min Act: -0.0001

Data Index: 974395 (C4 (Web Text))

Max Activating Token Index: 119

Text #3

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0361. Min Act: -0.0001

Data Index: 1214514 (C4 (Web Text))

Max Activating Token Index: 54

Text #4

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0313. Min Act: -0.0001

Data Index: 857200 (C4 (Web Text))

Max Activating Token Index: 569

Text #5

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0355. Min Act: -0.0001

Data Index: 168673 (C4 (Web Text))

Max Activating Token Index: 364

Text #6

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0318. Min Act: -0.0001

Data Index: 1188011 (C4 (Web Text))

Max Activating Token Index: 593

Text #7

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0323. Min Act: -0.0001

Data Index: 125818 (C4 (Web Text))

Max Activating Token Index: 59

Text #8

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0272. Min Act: -0.0001

Data Index: 198997 (C4 (Web Text))

Max Activating Token Index: 116

Text #9

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0305. Min Act: -0.0001

Data Index: 794096 (C4 (Web Text))

Max Activating Token Index: 558

Text #10

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0312. Min Act: -0.0001

Data Index: 512242 (C4 (Web Text))

Max Activating Token Index: 390

Text #11

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0295. Min Act: -0.0001

Data Index: 791232 (C4 (Web Text))

Max Activating Token Index: 927

Text #12

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0293. Min Act: -0.0001

Data Index: 1022609 (C4 (Web Text))

Max Activating Token Index: 409

Text #13

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0286. Min Act: -0.0001

Data Index: 940528 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0280. Min Act: -0.0001

Data Index: 792275 (C4 (Web Text))

Max Activating Token Index: 520

Text #15

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0329. Min Act: -0.0001

Data Index: 797124 (C4 (Web Text))

Max Activating Token Index: 274

Text #16

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0266. Min Act: -0.0001

Data Index: 1105402 (C4 (Web Text))

Max Activating Token Index: 56

Text #17

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0283. Min Act: -0.0001

Data Index: 1175815 (C4 (Web Text))

Max Activating Token Index: 37

Text #18

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0280. Min Act: -0.0001

Data Index: 62563 (C4 (Web Text))

Max Activating Token Index: 510

Text #19

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0254. Min Act: -0.0001

Data Index: 94775 (C4 (Web Text))

Max Activating Token Index: 258