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

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

Neuron 4304 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: 1.2689. Min Range: -1.2689

Max Act: 1.2689. Min Act: -0.0002

Data Index: 1255761 (C4 (Web Text))

Max Activating Token Index: 747

Text #1

Max Range: 1.2689. Min Range: -1.2689

Max Act: 1.2273. Min Act: -0.0002

Data Index: 1237870 (C4 (Web Text))

Max Activating Token Index: 62

Text #2

Max Range: 1.2689. Min Range: -1.2689

Max Act: 1.2557. Min Act: -0.0002

Data Index: 862483 (C4 (Web Text))

Max Activating Token Index: 432

Text #3

Max Range: 1.2689. Min Range: -1.2689

Max Act: 1.2465. Min Act: -0.0002

Data Index: 689394 (C4 (Web Text))

Max Activating Token Index: 92

Text #4

Max Range: 1.2689. Min Range: -1.2689

Max Act: 1.2258. Min Act: -0.0002

Data Index: 995105 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 1.2689. Min Range: -1.2689

Max Act: 1.1967. Min Act: -0.0002

Data Index: 667471 (C4 (Web Text))

Max Activating Token Index: 763

Text #6

Max Range: 1.2689. Min Range: -1.2689

Max Act: 1.1967. Min Act: -0.0002

Data Index: 249892 (C4 (Web Text))

Max Activating Token Index: 767

Text #7

Max Range: 1.2689. Min Range: -1.2689

Max Act: 1.1863. Min Act: -0.0002

Data Index: 525018 (C4 (Web Text))

Max Activating Token Index: 451

Text #8

Max Range: 1.2689. Min Range: -1.2689

Max Act: 1.2197. Min Act: -0.0002

Data Index: 583507 (C4 (Web Text))

Max Activating Token Index: 315

Text #9

Max Range: 1.2689. Min Range: -1.2689

Max Act: 1.2030. Min Act: -0.0002

Data Index: 418903 (C4 (Web Text))

Max Activating Token Index: 265

Text #10

Max Range: 1.2689. Min Range: -1.2689

Max Act: 1.2325. Min Act: -0.0002

Data Index: 894214 (C4 (Web Text))

Max Activating Token Index: 681

Text #11

Max Range: 1.2689. Min Range: -1.2689

Max Act: 1.1794. Min Act: -0.0002

Data Index: 1286548 (C4 (Web Text))

Max Activating Token Index: 619

Text #12

Max Range: 1.2689. Min Range: -1.2689

Max Act: 1.1742. Min Act: -0.0002

Data Index: 387835 (C4 (Web Text))

Max Activating Token Index: 810

Text #13

Max Range: 1.2689. Min Range: -1.2689

Max Act: 1.1489. Min Act: -0.0002

Data Index: 1322379 (C4 (Web Text))

Max Activating Token Index: 2

Text #14

Max Range: 1.2689. Min Range: -1.2689

Max Act: 1.1565. Min Act: -0.0002

Data Index: 97136 (C4 (Web Text))

Max Activating Token Index: 192

Text #15

Max Range: 1.2689. Min Range: -1.2689

Max Act: 1.1336. Min Act: -0.0002

Data Index: 1377255 (Python Code)

Max Activating Token Index: 474

Text #16

Max Range: 1.2689. Min Range: -1.2689

Max Act: 1.1566. Min Act: -0.0002

Data Index: 830582 (C4 (Web Text))

Max Activating Token Index: 194

Text #17

Max Range: 1.2689. Min Range: -1.2689

Max Act: 1.1296. Min Act: -0.0002

Data Index: 635724 (C4 (Web Text))

Max Activating Token Index: 224

Text #18

Max Range: 1.2689. Min Range: -1.2689

Max Act: 1.1298. Min Act: -0.0002

Data Index: 1173569 (C4 (Web Text))

Max Activating Token Index: 15

Text #19

Max Range: 1.2689. Min Range: -1.2689

Max Act: 1.1422. Min Act: -0.0002

Data Index: 1171456 (C4 (Web Text))

Max Activating Token Index: 207