Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1768 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3615. Min Range: -0.3615

Max Act: 0.3615. Min Act: -0.0001

Data Index: 1535686 (Python Code)

Max Activating Token Index: 411

Text #1

Max Range: 0.3615. Min Range: -0.3615

Max Act: 0.3292. Min Act: -0.0001

Data Index: 1605656 (Python Code)

Max Activating Token Index: 341

Text #2

Max Range: 0.3615. Min Range: -0.3615

Max Act: 0.3350. Min Act: -0.0001

Data Index: 1536964 (Python Code)

Max Activating Token Index: 978

Text #3

Max Range: 0.3615. Min Range: -0.3615

Max Act: 0.3218. Min Act: -0.0001

Data Index: 1589554 (Python Code)

Max Activating Token Index: 983

Text #4

Max Range: 0.3615. Min Range: -0.3615

Max Act: 0.3324. Min Act: -0.0001

Data Index: 1519783 (Python Code)

Max Activating Token Index: 740

Text #5

Max Range: 0.3615. Min Range: -0.3615

Max Act: 0.3088. Min Act: -0.0001

Data Index: 1648413 (Python Code)

Max Activating Token Index: 684

Text #6

Max Range: 0.3615. Min Range: -0.3615

Max Act: 0.3382. Min Act: -0.0001

Data Index: 1487277 (Python Code)

Max Activating Token Index: 176

Text #7

Max Range: 0.3615. Min Range: -0.3615

Max Act: 0.3170. Min Act: -0.0001

Data Index: 1547584 (Python Code)

Max Activating Token Index: 67

Text #8

Max Range: 0.3615. Min Range: -0.3615

Max Act: 0.3364. Min Act: -0.0001

Data Index: 1192193 (C4 (Web Text))

Max Activating Token Index: 316

Text #9

Max Range: 0.3615. Min Range: -0.3615

Max Act: 0.3255. Min Act: -0.0001

Data Index: 1603433 (Python Code)

Max Activating Token Index: 1017

Text #10

Max Range: 0.3615. Min Range: -0.3615

Max Act: 0.3223. Min Act: -0.0001

Data Index: 1601452 (Python Code)

Max Activating Token Index: 1003

Text #11

Max Range: 0.3615. Min Range: -0.3615

Max Act: 0.3332. Min Act: -0.0001

Data Index: 1554645 (Python Code)

Max Activating Token Index: 291

Text #12

Max Range: 0.3615. Min Range: -0.3615

Max Act: 0.3317. Min Act: -0.0001

Data Index: 1412795 (Python Code)

Max Activating Token Index: 887

Text #13

Max Range: 0.3615. Min Range: -0.3615

Max Act: 0.3184. Min Act: -0.0001

Data Index: 1415258 (Python Code)

Max Activating Token Index: 732

Text #14

Max Range: 0.3615. Min Range: -0.3615

Max Act: 0.3196. Min Act: -0.0001

Data Index: 1479316 (Python Code)

Max Activating Token Index: 1011

Text #15

Max Range: 0.3615. Min Range: -0.3615

Max Act: 0.3394. Min Act: -0.0001

Data Index: 1593088 (Python Code)

Max Activating Token Index: 921

Text #16

Max Range: 0.3615. Min Range: -0.3615

Max Act: 0.3183. Min Act: -0.0001

Data Index: 1362714 (Python Code)

Max Activating Token Index: 334

Text #17

Max Range: 0.3615. Min Range: -0.3615

Max Act: 0.3277. Min Act: -0.0001

Data Index: 1437525 (Python Code)

Max Activating Token Index: 67

Text #18

Max Range: 0.3615. Min Range: -0.3615

Max Act: 0.2949. Min Act: -0.0001

Data Index: 1362162 (Python Code)

Max Activating Token Index: 575

Text #19

Max Range: 0.3615. Min Range: -0.3615

Max Act: 0.3137. Min Act: -0.0001

Data Index: 1488827 (Python Code)

Max Activating Token Index: 31