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

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

Neuron 2311 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0615. Min Act: -0.0000

Data Index: 758922 (C4 (Web Text))

Max Activating Token Index: 531

Text #1

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0382. Min Act: -0.0000

Data Index: 1298141 (C4 (Web Text))

Max Activating Token Index: 473

Text #2

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0368. Min Act: -0.0000

Data Index: 1580261 (Python Code)

Max Activating Token Index: 347

Text #3

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0405. Min Act: -0.0000

Data Index: 1360209 (Python Code)

Max Activating Token Index: 782

Text #4

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0353. Min Act: -0.0000

Data Index: 950511 (C4 (Web Text))

Max Activating Token Index: 214

Text #5

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0362. Min Act: -0.0000

Data Index: 1649538 (Python Code)

Max Activating Token Index: 99

Text #6

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0337. Min Act: -0.0000

Data Index: 1615361 (Python Code)

Max Activating Token Index: 10

Text #7

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0333. Min Act: -0.0000

Data Index: 1404414 (Python Code)

Max Activating Token Index: 167

Text #8

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0362. Min Act: -0.0000

Data Index: 1041593 (C4 (Web Text))

Max Activating Token Index: 69

Text #9

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0327. Min Act: -0.0000

Data Index: 265609 (C4 (Web Text))

Max Activating Token Index: 130

Text #10

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0316. Min Act: -0.0000

Data Index: 978438 (C4 (Web Text))

Max Activating Token Index: 341

Text #11

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0369. Min Act: -0.0000

Data Index: 1395129 (Python Code)

Max Activating Token Index: 311

Text #12

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0330. Min Act: -0.0000

Data Index: 762487 (C4 (Web Text))

Max Activating Token Index: 106

Text #13

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0294. Min Act: -0.0000

Data Index: 727765 (C4 (Web Text))

Max Activating Token Index: 794

Text #14

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0325. Min Act: -0.0000

Data Index: 614559 (C4 (Web Text))

Max Activating Token Index: 717

Text #15

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0309. Min Act: -0.0000

Data Index: 1196403 (C4 (Web Text))

Max Activating Token Index: 472

Text #16

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0321. Min Act: -0.0000

Data Index: 1564860 (Python Code)

Max Activating Token Index: 131

Text #17

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0303. Min Act: -0.0000

Data Index: 1108147 (C4 (Web Text))

Max Activating Token Index: 221

Text #18

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0296. Min Act: -0.0000

Data Index: 478613 (C4 (Web Text))

Max Activating Token Index: 927

Text #19

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0309. Min Act: -0.0000

Data Index: 1162611 (C4 (Web Text))

Max Activating Token Index: 1000