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

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

Neuron 4358 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5977. Min Range: -2.5977

Max Act: 2.5977. Min Act: -0.0000

Data Index: 1556309 (Python Code)

Max Activating Token Index: 151

Text #1

Max Range: 2.5977. Min Range: -2.5977

Max Act: 2.3852. Min Act: -0.0000

Data Index: 1556324 (Python Code)

Max Activating Token Index: 421

Text #2

Max Range: 2.5977. Min Range: -2.5977

Max Act: 2.2280. Min Act: -0.0000

Data Index: 1414228 (Python Code)

Max Activating Token Index: 425

Text #3

Max Range: 2.5977. Min Range: -2.5977

Max Act: 2.3461. Min Act: -0.0000

Data Index: 1364297 (Python Code)

Max Activating Token Index: 167

Text #4

Max Range: 2.5977. Min Range: -2.5977

Max Act: 2.3531. Min Act: -0.0000

Data Index: 1477972 (Python Code)

Max Activating Token Index: 375

Text #5

Max Range: 2.5977. Min Range: -2.5977

Max Act: 2.3295. Min Act: -0.0001

Data Index: 1373383 (Python Code)

Max Activating Token Index: 192

Text #6

Max Range: 2.5977. Min Range: -2.5977

Max Act: 2.3199. Min Act: -0.0000

Data Index: 1360472 (Python Code)

Max Activating Token Index: 203

Text #7

Max Range: 2.5977. Min Range: -2.5977

Max Act: 2.1971. Min Act: -0.0001

Data Index: 1537715 (Python Code)

Max Activating Token Index: 216

Text #8

Max Range: 2.5977. Min Range: -2.5977

Max Act: 2.3969. Min Act: -0.0001

Data Index: 1472835 (Python Code)

Max Activating Token Index: 12

Text #9

Max Range: 2.5977. Min Range: -2.5977

Max Act: 2.2524. Min Act: -0.0000

Data Index: 1441716 (Python Code)

Max Activating Token Index: 126

Text #10

Max Range: 2.5977. Min Range: -2.5977

Max Act: 2.1182. Min Act: -0.0000

Data Index: 1560229 (Python Code)

Max Activating Token Index: 59

Text #11

Max Range: 2.5977. Min Range: -2.5977

Max Act: 2.3388. Min Act: -0.0000

Data Index: 1445989 (Python Code)

Max Activating Token Index: 123

Text #12

Max Range: 2.5977. Min Range: -2.5977

Max Act: 1.9994. Min Act: -0.0001

Data Index: 1437882 (Python Code)

Max Activating Token Index: 781

Text #13

Max Range: 2.5977. Min Range: -2.5977

Max Act: 2.1729. Min Act: -0.0000

Data Index: 1460833 (Python Code)

Max Activating Token Index: 224

Text #14

Max Range: 2.5977. Min Range: -2.5977

Max Act: 2.1692. Min Act: -0.0001

Data Index: 1372875 (Python Code)

Max Activating Token Index: 66

Text #15

Max Range: 2.5977. Min Range: -2.5977

Max Act: 2.2766. Min Act: -0.0000

Data Index: 1388844 (Python Code)

Max Activating Token Index: 798

Text #16

Max Range: 2.5977. Min Range: -2.5977

Max Act: 2.1550. Min Act: -0.0001

Data Index: 1650174 (Python Code)

Max Activating Token Index: 138

Text #17

Max Range: 2.5977. Min Range: -2.5977

Max Act: 2.1111. Min Act: -0.0000

Data Index: 1538821 (Python Code)

Max Activating Token Index: 439

Text #18

Max Range: 2.5977. Min Range: -2.5977

Max Act: 2.0838. Min Act: -0.0000

Data Index: 1631497 (Python Code)

Max Activating Token Index: 30

Text #19

Max Range: 2.5977. Min Range: -2.5977

Max Act: 2.1618. Min Act: -0.0001

Data Index: 1575084 (Python Code)

Max Activating Token Index: 52