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

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

Neuron 1429 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7393. Min Range: -1.7393

Max Act: 1.7393. Min Act: -0.0000

Data Index: 347410 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 1.7393. Min Range: -1.7393

Max Act: 1.6613. Min Act: -0.0000

Data Index: 8975 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 1.7393. Min Range: -1.7393

Max Act: 1.6407. Min Act: -0.0000

Data Index: 66270 (C4 (Web Text))

Max Activating Token Index: 746

Text #3

Max Range: 1.7393. Min Range: -1.7393

Max Act: 1.5683. Min Act: -0.0000

Data Index: 101552 (C4 (Web Text))

Max Activating Token Index: 321

Text #4

Max Range: 1.7393. Min Range: -1.7393

Max Act: 1.5577. Min Act: -0.0000

Data Index: 781223 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 1.7393. Min Range: -1.7393

Max Act: 1.6402. Min Act: -0.0000

Data Index: 394653 (C4 (Web Text))

Max Activating Token Index: 328

Text #6

Max Range: 1.7393. Min Range: -1.7393

Max Act: 1.5157. Min Act: -0.0000

Data Index: 473521 (C4 (Web Text))

Max Activating Token Index: 377

Text #7

Max Range: 1.7393. Min Range: -1.7393

Max Act: 1.4667. Min Act: -0.0000

Data Index: 529403 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 1.7393. Min Range: -1.7393

Max Act: 1.4929. Min Act: -0.0000

Data Index: 35154 (C4 (Web Text))

Max Activating Token Index: 514

Text #9

Max Range: 1.7393. Min Range: -1.7393

Max Act: 1.3956. Min Act: -0.0000

Data Index: 1018718 (C4 (Web Text))

Max Activating Token Index: 505

Text #10

Max Range: 1.7393. Min Range: -1.7393

Max Act: 1.4309. Min Act: -0.0000

Data Index: 1322624 (C4 (Web Text))

Max Activating Token Index: 64

Text #11

Max Range: 1.7393. Min Range: -1.7393

Max Act: 1.4166. Min Act: -0.0000

Data Index: 1296144 (C4 (Web Text))

Max Activating Token Index: 502

Text #12

Max Range: 1.7393. Min Range: -1.7393

Max Act: 1.4448. Min Act: -0.0000

Data Index: 1310392 (C4 (Web Text))

Max Activating Token Index: 346

Text #13

Max Range: 1.7393. Min Range: -1.7393

Max Act: 1.4089. Min Act: -0.0000

Data Index: 716534 (C4 (Web Text))

Max Activating Token Index: 334

Text #14

Max Range: 1.7393. Min Range: -1.7393

Max Act: 1.4644. Min Act: -0.0000

Data Index: 1091880 (C4 (Web Text))

Max Activating Token Index: 355

Text #15

Max Range: 1.7393. Min Range: -1.7393

Max Act: 1.4273. Min Act: -0.0000

Data Index: 218171 (C4 (Web Text))

Max Activating Token Index: 730

Text #16

Max Range: 1.7393. Min Range: -1.7393

Max Act: 1.4229. Min Act: -0.0000

Data Index: 708906 (C4 (Web Text))

Max Activating Token Index: 438

Text #17

Max Range: 1.7393. Min Range: -1.7393

Max Act: 1.3892. Min Act: -0.0000

Data Index: 131950 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 1.7393. Min Range: -1.7393

Max Act: 1.4238. Min Act: -0.0000

Data Index: 735085 (C4 (Web Text))

Max Activating Token Index: 45

Text #19

Max Range: 1.7393. Min Range: -1.7393

Max Act: 1.3399. Min Act: -0.0000

Data Index: 586901 (C4 (Web Text))

Max Activating Token Index: 208