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

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

Neuron 4580 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.3161. Min Act: -0.0000

Data Index: 818662 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2731. Min Act: -0.0000

Data Index: 401574 (C4 (Web Text))

Max Activating Token Index: 723

Text #2

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2809. Min Act: -0.0000

Data Index: 1021398 (C4 (Web Text))

Max Activating Token Index: 451

Text #3

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2564. Min Act: -0.0000

Data Index: 294810 (C4 (Web Text))

Max Activating Token Index: 357

Text #4

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2680. Min Act: -0.0000

Data Index: 749837 (C4 (Web Text))

Max Activating Token Index: 723

Text #5

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2576. Min Act: -0.0000

Data Index: 270382 (C4 (Web Text))

Max Activating Token Index: 429

Text #6

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2382. Min Act: -0.0000

Data Index: 648653 (C4 (Web Text))

Max Activating Token Index: 311

Text #7

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2460. Min Act: -0.0000

Data Index: 591026 (C4 (Web Text))

Max Activating Token Index: 185

Text #8

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2518. Min Act: -0.0000

Data Index: 835580 (C4 (Web Text))

Max Activating Token Index: 54

Text #9

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2520. Min Act: -0.0000

Data Index: 173545 (C4 (Web Text))

Max Activating Token Index: 903

Text #10

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2336. Min Act: -0.0000

Data Index: 216925 (C4 (Web Text))

Max Activating Token Index: 93

Text #11

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2402. Min Act: -0.0000

Data Index: 151216 (C4 (Web Text))

Max Activating Token Index: 1012

Text #12

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2162. Min Act: -0.0000

Data Index: 761358 (C4 (Web Text))

Max Activating Token Index: 989

Text #13

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2193. Min Act: -0.0000

Data Index: 757971 (C4 (Web Text))

Max Activating Token Index: 335

Text #14

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2346. Min Act: -0.0000

Data Index: 913561 (C4 (Web Text))

Max Activating Token Index: 150

Text #15

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2268. Min Act: -0.0000

Data Index: 953667 (C4 (Web Text))

Max Activating Token Index: 131

Text #16

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2252. Min Act: -0.0000

Data Index: 614277 (C4 (Web Text))

Max Activating Token Index: 339

Text #17

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2394. Min Act: -0.0000

Data Index: 77056 (C4 (Web Text))

Max Activating Token Index: 803

Text #18

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2139. Min Act: -0.0000

Data Index: 675091 (C4 (Web Text))

Max Activating Token Index: 961

Text #19

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2202. Min Act: -0.0000

Data Index: 11826 (C4 (Web Text))

Max Activating Token Index: 258