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

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

Neuron 5067 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0173. Min Range: -5.0173

Max Act: 4.9406. Min Act: -0.0000

Data Index: 243824 (C4 (Web Text))

Max Activating Token Index: 210

Text #1

Max Range: 5.0173. Min Range: -5.0173

Max Act: 4.9178. Min Act: -0.0000

Data Index: 270035 (C4 (Web Text))

Max Activating Token Index: 627

Text #2

Max Range: 5.0173. Min Range: -5.0173

Max Act: 4.9269. Min Act: -0.0000

Data Index: 1362101 (Python Code)

Max Activating Token Index: 341

Text #3

Max Range: 5.0173. Min Range: -5.0173

Max Act: 5.0173. Min Act: -0.0000

Data Index: 1610595 (Python Code)

Max Activating Token Index: 72

Text #4

Max Range: 5.0173. Min Range: -5.0173

Max Act: 4.4917. Min Act: -0.0000

Data Index: 1030657 (C4 (Web Text))

Max Activating Token Index: 254

Text #5

Max Range: 5.0173. Min Range: -5.0173

Max Act: 4.6816. Min Act: -0.0000

Data Index: 1430098 (Python Code)

Max Activating Token Index: 81

Text #6

Max Range: 5.0173. Min Range: -5.0173

Max Act: 4.3327. Min Act: -0.0000

Data Index: 1523288 (Python Code)

Max Activating Token Index: 921

Text #7

Max Range: 5.0173. Min Range: -5.0173

Max Act: 4.5028. Min Act: -0.0000

Data Index: 259690 (C4 (Web Text))

Max Activating Token Index: 272

Text #8

Max Range: 5.0173. Min Range: -5.0173

Max Act: 4.4644. Min Act: -0.0000

Data Index: 1481135 (Python Code)

Max Activating Token Index: 11

Text #9

Max Range: 5.0173. Min Range: -5.0173

Max Act: 4.6395. Min Act: -0.0000

Data Index: 786767 (C4 (Web Text))

Max Activating Token Index: 723

Text #10

Max Range: 5.0173. Min Range: -5.0173

Max Act: 4.5997. Min Act: -0.0000

Data Index: 290185 (C4 (Web Text))

Max Activating Token Index: 625

Text #11

Max Range: 5.0173. Min Range: -5.0173

Max Act: 4.3939. Min Act: -0.0000

Data Index: 1210416 (C4 (Web Text))

Max Activating Token Index: 694

Text #12

Max Range: 5.0173. Min Range: -5.0173

Max Act: 4.2446. Min Act: -0.0000

Data Index: 555197 (C4 (Web Text))

Max Activating Token Index: 693

Text #13

Max Range: 5.0173. Min Range: -5.0173

Max Act: 4.4030. Min Act: -0.0000

Data Index: 787933 (C4 (Web Text))

Max Activating Token Index: 901

Text #14

Max Range: 5.0173. Min Range: -5.0173

Max Act: 4.4763. Min Act: -0.0000

Data Index: 6625 (C4 (Web Text))

Max Activating Token Index: 281

Text #15

Max Range: 5.0173. Min Range: -5.0173

Max Act: 4.4814. Min Act: -0.0000

Data Index: 779354 (C4 (Web Text))

Max Activating Token Index: 393

Text #16

Max Range: 5.0173. Min Range: -5.0173

Max Act: 4.1244. Min Act: -0.0000

Data Index: 965737 (C4 (Web Text))

Max Activating Token Index: 379

Text #17

Max Range: 5.0173. Min Range: -5.0173

Max Act: 4.1214. Min Act: -0.0000

Data Index: 417810 (C4 (Web Text))

Max Activating Token Index: 15

Text #18

Max Range: 5.0173. Min Range: -5.0173

Max Act: 4.4494. Min Act: -0.0000

Data Index: 1001265 (C4 (Web Text))

Max Activating Token Index: 630

Text #19

Max Range: 5.0173. Min Range: -5.0173

Max Act: 4.4517. Min Act: -0.0000

Data Index: 503214 (C4 (Web Text))

Max Activating Token Index: 558