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

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

Neuron 3091 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7595. Min Range: -1.7595

Max Act: 1.7272. Min Act: -0.0001

Data Index: 1640378 (Python Code)

Max Activating Token Index: 93

Text #1

Max Range: 1.7595. Min Range: -1.7595

Max Act: 1.7595. Min Act: -0.0001

Data Index: 1568704 (Python Code)

Max Activating Token Index: 3

Text #2

Max Range: 1.7595. Min Range: -1.7595

Max Act: 1.7595. Min Act: -0.0001

Data Index: 1557351 (Python Code)

Max Activating Token Index: 3

Text #3

Max Range: 1.7595. Min Range: -1.7595

Max Act: 1.7242. Min Act: -0.0001

Data Index: 1378289 (Python Code)

Max Activating Token Index: 86

Text #4

Max Range: 1.7595. Min Range: -1.7595

Max Act: 1.6855. Min Act: -0.0000

Data Index: 1632526 (Python Code)

Max Activating Token Index: 8

Text #5

Max Range: 1.7595. Min Range: -1.7595

Max Act: 1.6276. Min Act: -0.0001

Data Index: 1461163 (Python Code)

Max Activating Token Index: 104

Text #6

Max Range: 1.7595. Min Range: -1.7595

Max Act: 1.7138. Min Act: -0.0001

Data Index: 1592228 (Python Code)

Max Activating Token Index: 11

Text #7

Max Range: 1.7595. Min Range: -1.7595

Max Act: 1.6080. Min Act: -0.0000

Data Index: 1493234 (Python Code)

Max Activating Token Index: 632

Text #8

Max Range: 1.7595. Min Range: -1.7595

Max Act: 1.6200. Min Act: -0.0000

Data Index: 1428622 (Python Code)

Max Activating Token Index: 431

Text #9

Max Range: 1.7595. Min Range: -1.7595

Max Act: 1.7466. Min Act: -0.0001

Data Index: 1449208 (Python Code)

Max Activating Token Index: 446

Text #10

Max Range: 1.7595. Min Range: -1.7595

Max Act: 1.6171. Min Act: -0.0001

Data Index: 1493263 (Python Code)

Max Activating Token Index: 7

Text #11

Max Range: 1.7595. Min Range: -1.7595

Max Act: 1.5980. Min Act: -0.0001

Data Index: 1617971 (Python Code)

Max Activating Token Index: 3

Text #12

Max Range: 1.7595. Min Range: -1.7595

Max Act: 1.6369. Min Act: -0.0001

Data Index: 1408577 (Python Code)

Max Activating Token Index: 68

Text #13

Max Range: 1.7595. Min Range: -1.7595

Max Act: 1.6185. Min Act: -0.0000

Data Index: 1478539 (Python Code)

Max Activating Token Index: 508

Text #14

Max Range: 1.7595. Min Range: -1.7595

Max Act: 1.5260. Min Act: -0.0001

Data Index: 1637777 (Python Code)

Max Activating Token Index: 10

Text #15

Max Range: 1.7595. Min Range: -1.7595

Max Act: 1.5615. Min Act: -0.0001

Data Index: 1367918 (Python Code)

Max Activating Token Index: 54

Text #16

Max Range: 1.7595. Min Range: -1.7595

Max Act: 1.5177. Min Act: -0.0001

Data Index: 1500391 (Python Code)

Max Activating Token Index: 40

Text #17

Max Range: 1.7595. Min Range: -1.7595

Max Act: 1.5566. Min Act: -0.0001

Data Index: 1617044 (Python Code)

Max Activating Token Index: 816

Text #18

Max Range: 1.7595. Min Range: -1.7595

Max Act: 1.5366. Min Act: -0.0000

Data Index: 1431496 (Python Code)

Max Activating Token Index: 69

Text #19

Max Range: 1.7595. Min Range: -1.7595

Max Act: 1.4992. Min Act: -0.0001

Data Index: 1493206 (Python Code)

Max Activating Token Index: 157