Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2123 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2696. Min Act: -0.0001

Data Index: 1125311 (C4 (Web Text))

Max Activating Token Index: 865

Text #1

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2641. Min Act: -0.0000

Data Index: 458446 (C4 (Web Text))

Max Activating Token Index: 387

Text #2

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2574. Min Act: -0.0000

Data Index: 952056 (C4 (Web Text))

Max Activating Token Index: 591

Text #3

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2650. Min Act: -0.0001

Data Index: 613551 (C4 (Web Text))

Max Activating Token Index: 306

Text #4

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2656. Min Act: -0.0000

Data Index: 644152 (C4 (Web Text))

Max Activating Token Index: 976

Text #5

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2396. Min Act: -0.0001

Data Index: 950030 (C4 (Web Text))

Max Activating Token Index: 845

Text #6

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2702. Min Act: -0.0001

Data Index: 983815 (C4 (Web Text))

Max Activating Token Index: 1000

Text #7

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2404. Min Act: -0.0000

Data Index: 904522 (C4 (Web Text))

Max Activating Token Index: 284

Text #8

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2431. Min Act: -0.0000

Data Index: 398270 (C4 (Web Text))

Max Activating Token Index: 465

Text #9

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2357. Min Act: -0.0001

Data Index: 1317640 (C4 (Web Text))

Max Activating Token Index: 364

Text #10

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2240. Min Act: -0.0000

Data Index: 60235 (C4 (Web Text))

Max Activating Token Index: 755

Text #11

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2292. Min Act: -0.0000

Data Index: 1058774 (C4 (Web Text))

Max Activating Token Index: 220

Text #12

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2243. Min Act: -0.0000

Data Index: 417303 (C4 (Web Text))

Max Activating Token Index: 768

Text #13

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2305. Min Act: -0.0000

Data Index: 1293399 (C4 (Web Text))

Max Activating Token Index: 79

Text #14

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2477. Min Act: -0.0000

Data Index: 961643 (C4 (Web Text))

Max Activating Token Index: 402

Text #15

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2041. Min Act: -0.0001

Data Index: 412556 (C4 (Web Text))

Max Activating Token Index: 686

Text #16

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2233. Min Act: -0.0000

Data Index: 1250032 (C4 (Web Text))

Max Activating Token Index: 371

Text #17

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2236. Min Act: -0.0000

Data Index: 1257074 (C4 (Web Text))

Max Activating Token Index: 993

Text #18

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2149. Min Act: -0.0000

Data Index: 331473 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2312. Min Act: -0.0000

Data Index: 33265 (C4 (Web Text))

Max Activating Token Index: 161