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

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

Neuron 1766 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: 0.4387. Min Range: -0.4387

Max Act: 0.4387. Min Act: -0.0000

Data Index: 791485 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.3429. Min Act: -0.0000

Data Index: 801475 (C4 (Web Text))

Max Activating Token Index: 68

Text #2

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.3025. Min Act: -0.0000

Data Index: 76553 (C4 (Web Text))

Max Activating Token Index: 405

Text #3

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2977. Min Act: -0.0000

Data Index: 180394 (C4 (Web Text))

Max Activating Token Index: 415

Text #4

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.3381. Min Act: -0.0000

Data Index: 179273 (C4 (Web Text))

Max Activating Token Index: 391

Text #5

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2964. Min Act: -0.0000

Data Index: 518761 (C4 (Web Text))

Max Activating Token Index: 392

Text #6

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2718. Min Act: -0.0000

Data Index: 1081440 (C4 (Web Text))

Max Activating Token Index: 44

Text #7

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2822. Min Act: -0.0000

Data Index: 512328 (C4 (Web Text))

Max Activating Token Index: 165

Text #8

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2400. Min Act: -0.0000

Data Index: 1154139 (C4 (Web Text))

Max Activating Token Index: 651

Text #9

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2978. Min Act: -0.0000

Data Index: 906179 (C4 (Web Text))

Max Activating Token Index: 393

Text #10

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.3304. Min Act: -0.0000

Data Index: 560722 (C4 (Web Text))

Max Activating Token Index: 786

Text #11

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2440. Min Act: -0.0000

Data Index: 232599 (C4 (Web Text))

Max Activating Token Index: 308

Text #12

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2224. Min Act: -0.0001

Data Index: 1192406 (C4 (Web Text))

Max Activating Token Index: 271

Text #13

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2458. Min Act: -0.0000

Data Index: 82580 (C4 (Web Text))

Max Activating Token Index: 455

Text #14

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2109. Min Act: -0.0000

Data Index: 421411 (C4 (Web Text))

Max Activating Token Index: 375

Text #15

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2342. Min Act: -0.0000

Data Index: 663077 (C4 (Web Text))

Max Activating Token Index: 574

Text #16

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2465. Min Act: -0.0000

Data Index: 387487 (C4 (Web Text))

Max Activating Token Index: 319

Text #17

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2207. Min Act: -0.0000

Data Index: 585504 (C4 (Web Text))

Max Activating Token Index: 370

Text #18

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2260. Min Act: -0.0000

Data Index: 628974 (C4 (Web Text))

Max Activating Token Index: 912

Text #19

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2291. Min Act: -0.0000

Data Index: 176204 (C4 (Web Text))

Max Activating Token Index: 364