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

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

Neuron 1800 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 1.4976. Min Range: -1.4976

Max Act: 1.4976. Min Act: -0.0002

Data Index: 1026978 (C4 (Web Text))

Max Activating Token Index: 257

Text #1

Max Range: 1.4976. Min Range: -1.4976

Max Act: 1.4149. Min Act: -0.0002

Data Index: 253959 (C4 (Web Text))

Max Activating Token Index: 641

Text #2

Max Range: 1.4976. Min Range: -1.4976

Max Act: 1.3945. Min Act: -0.0002

Data Index: 368317 (C4 (Web Text))

Max Activating Token Index: 252

Text #3

Max Range: 1.4976. Min Range: -1.4976

Max Act: 1.3833. Min Act: -0.0003

Data Index: 325137 (C4 (Web Text))

Max Activating Token Index: 285

Text #4

Max Range: 1.4976. Min Range: -1.4976

Max Act: 1.3149. Min Act: -0.0002

Data Index: 689324 (C4 (Web Text))

Max Activating Token Index: 487

Text #5

Max Range: 1.4976. Min Range: -1.4976

Max Act: 1.2979. Min Act: -0.0002

Data Index: 103496 (C4 (Web Text))

Max Activating Token Index: 498

Text #6

Max Range: 1.4976. Min Range: -1.4976

Max Act: 1.2813. Min Act: -0.0002

Data Index: 710438 (C4 (Web Text))

Max Activating Token Index: 749

Text #7

Max Range: 1.4976. Min Range: -1.4976

Max Act: 1.2982. Min Act: -0.0002

Data Index: 1220483 (C4 (Web Text))

Max Activating Token Index: 387

Text #8

Max Range: 1.4976. Min Range: -1.4976

Max Act: 1.2813. Min Act: -0.0002

Data Index: 605461 (C4 (Web Text))

Max Activating Token Index: 841

Text #9

Max Range: 1.4976. Min Range: -1.4976

Max Act: 1.3004. Min Act: -0.0002

Data Index: 1073552 (C4 (Web Text))

Max Activating Token Index: 582

Text #10

Max Range: 1.4976. Min Range: -1.4976

Max Act: 1.2740. Min Act: -0.0002

Data Index: 218860 (C4 (Web Text))

Max Activating Token Index: 455

Text #11

Max Range: 1.4976. Min Range: -1.4976

Max Act: 1.2888. Min Act: -0.0002

Data Index: 607370 (C4 (Web Text))

Max Activating Token Index: 741

Text #12

Max Range: 1.4976. Min Range: -1.4976

Max Act: 1.3006. Min Act: -0.0002

Data Index: 1358784 (C4 (Web Text))

Max Activating Token Index: 542

Text #13

Max Range: 1.4976. Min Range: -1.4976

Max Act: 1.2698. Min Act: -0.0002

Data Index: 148911 (C4 (Web Text))

Max Activating Token Index: 383

Text #14

Max Range: 1.4976. Min Range: -1.4976

Max Act: 1.2617. Min Act: -0.0002

Data Index: 822299 (C4 (Web Text))

Max Activating Token Index: 83

Text #15

Max Range: 1.4976. Min Range: -1.4976

Max Act: 1.2576. Min Act: -0.0002

Data Index: 1302323 (C4 (Web Text))

Max Activating Token Index: 181

Text #16

Max Range: 1.4976. Min Range: -1.4976

Max Act: 1.2368. Min Act: -0.0002

Data Index: 35317 (C4 (Web Text))

Max Activating Token Index: 344

Text #17

Max Range: 1.4976. Min Range: -1.4976

Max Act: 1.2736. Min Act: -0.0003

Data Index: 807680 (C4 (Web Text))

Max Activating Token Index: 239

Text #18

Max Range: 1.4976. Min Range: -1.4976

Max Act: 1.2450. Min Act: -0.0002

Data Index: 342620 (C4 (Web Text))

Max Activating Token Index: 421

Text #19

Max Range: 1.4976. Min Range: -1.4976

Max Act: 1.2516. Min Act: -0.0003

Data Index: 1224907 (C4 (Web Text))

Max Activating Token Index: 814