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

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

Neuron 1438 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: 1.7884. Min Range: -1.7884

Max Act: 1.7884. Min Act: -0.0001

Data Index: 1387076 (Python Code)

Max Activating Token Index: 442

Text #1

Max Range: 1.7884. Min Range: -1.7884

Max Act: 1.6624. Min Act: -0.0001

Data Index: 1623585 (Python Code)

Max Activating Token Index: 297

Text #2

Max Range: 1.7884. Min Range: -1.7884

Max Act: 1.5339. Min Act: -0.0001

Data Index: 1393132 (Python Code)

Max Activating Token Index: 962

Text #3

Max Range: 1.7884. Min Range: -1.7884

Max Act: 1.5280. Min Act: -0.0001

Data Index: 1394872 (Python Code)

Max Activating Token Index: 792

Text #4

Max Range: 1.7884. Min Range: -1.7884

Max Act: 1.4498. Min Act: -0.0001

Data Index: 1388493 (Python Code)

Max Activating Token Index: 179

Text #5

Max Range: 1.7884. Min Range: -1.7884

Max Act: 1.4773. Min Act: -0.0001

Data Index: 1563406 (Python Code)

Max Activating Token Index: 232

Text #6

Max Range: 1.7884. Min Range: -1.7884

Max Act: 1.3848. Min Act: -0.0001

Data Index: 1499184 (Python Code)

Max Activating Token Index: 440

Text #7

Max Range: 1.7884. Min Range: -1.7884

Max Act: 1.3915. Min Act: -0.0001

Data Index: 1497261 (Python Code)

Max Activating Token Index: 675

Text #8

Max Range: 1.7884. Min Range: -1.7884

Max Act: 1.2295. Min Act: -0.0001

Data Index: 1386213 (Python Code)

Max Activating Token Index: 213

Text #9

Max Range: 1.7884. Min Range: -1.7884

Max Act: 1.3857. Min Act: -0.0001

Data Index: 1538594 (Python Code)

Max Activating Token Index: 49

Text #10

Max Range: 1.7884. Min Range: -1.7884

Max Act: 1.3433. Min Act: -0.0001

Data Index: 1554059 (Python Code)

Max Activating Token Index: 65

Text #11

Max Range: 1.7884. Min Range: -1.7884

Max Act: 1.3726. Min Act: -0.0001

Data Index: 1652941 (Python Code)

Max Activating Token Index: 86

Text #12

Max Range: 1.7884. Min Range: -1.7884

Max Act: 1.3377. Min Act: -0.0001

Data Index: 1372592 (Python Code)

Max Activating Token Index: 76

Text #13

Max Range: 1.7884. Min Range: -1.7884

Max Act: 1.2117. Min Act: -0.0001

Data Index: 1528850 (Python Code)

Max Activating Token Index: 988

Text #14

Max Range: 1.7884. Min Range: -1.7884

Max Act: 1.3885. Min Act: -0.0001

Data Index: 1652289 (Python Code)

Max Activating Token Index: 516

Text #15

Max Range: 1.7884. Min Range: -1.7884

Max Act: 1.1851. Min Act: -0.0001

Data Index: 1577179 (Python Code)

Max Activating Token Index: 691

Text #16

Max Range: 1.7884. Min Range: -1.7884

Max Act: 1.1707. Min Act: -0.0001

Data Index: 1374416 (Python Code)

Max Activating Token Index: 239

Text #17

Max Range: 1.7884. Min Range: -1.7884

Max Act: 1.3334. Min Act: -0.0001

Data Index: 1557654 (Python Code)

Max Activating Token Index: 277

Text #18

Max Range: 1.7884. Min Range: -1.7884

Max Act: 1.2699. Min Act: -0.0001

Data Index: 1549249 (Python Code)

Max Activating Token Index: 113

Text #19

Max Range: 1.7884. Min Range: -1.7884

Max Act: 1.3213. Min Act: -0.0001

Data Index: 1415334 (Python Code)

Max Activating Token Index: 298