Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1429 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0640. Min Range: -1.0640

Max Act: 0.9971. Min Act: -0.0001

Data Index: 1471144 (Python Code)

Max Activating Token Index: 404

Text #1

Max Range: 1.0640. Min Range: -1.0640

Max Act: 0.9169. Min Act: -0.0001

Data Index: 1582416 (Python Code)

Max Activating Token Index: 153

Text #2

Max Range: 1.0640. Min Range: -1.0640

Max Act: 0.9091. Min Act: -0.0001

Data Index: 1528085 (Python Code)

Max Activating Token Index: 61

Text #3

Max Range: 1.0640. Min Range: -1.0640

Max Act: 1.0640. Min Act: -0.0001

Data Index: 1370149 (Python Code)

Max Activating Token Index: 656

Text #4

Max Range: 1.0640. Min Range: -1.0640

Max Act: 0.8594. Min Act: -0.0001

Data Index: 1446848 (Python Code)

Max Activating Token Index: 333

Text #5

Max Range: 1.0640. Min Range: -1.0640

Max Act: 0.8861. Min Act: -0.0001

Data Index: 1379114 (Python Code)

Max Activating Token Index: 145

Text #6

Max Range: 1.0640. Min Range: -1.0640

Max Act: 0.7922. Min Act: -0.0001

Data Index: 1558334 (Python Code)

Max Activating Token Index: 476

Text #7

Max Range: 1.0640. Min Range: -1.0640

Max Act: 0.8327. Min Act: -0.0001

Data Index: 1447224 (Python Code)

Max Activating Token Index: 644

Text #8

Max Range: 1.0640. Min Range: -1.0640

Max Act: 0.8185. Min Act: -0.0001

Data Index: 1541097 (Python Code)

Max Activating Token Index: 210

Text #9

Max Range: 1.0640. Min Range: -1.0640

Max Act: 0.8205. Min Act: -0.0001

Data Index: 1510304 (Python Code)

Max Activating Token Index: 418

Text #10

Max Range: 1.0640. Min Range: -1.0640

Max Act: 0.8207. Min Act: -0.0001

Data Index: 1642596 (Python Code)

Max Activating Token Index: 32

Text #11

Max Range: 1.0640. Min Range: -1.0640

Max Act: 0.8329. Min Act: -0.0001

Data Index: 1424278 (Python Code)

Max Activating Token Index: 470

Text #12

Max Range: 1.0640. Min Range: -1.0640

Max Act: 0.8464. Min Act: -0.0001

Data Index: 1523529 (Python Code)

Max Activating Token Index: 333

Text #13

Max Range: 1.0640. Min Range: -1.0640

Max Act: 0.8227. Min Act: -0.0001

Data Index: 1501849 (Python Code)

Max Activating Token Index: 440

Text #14

Max Range: 1.0640. Min Range: -1.0640

Max Act: 0.7865. Min Act: -0.0001

Data Index: 1531886 (Python Code)

Max Activating Token Index: 411

Text #15

Max Range: 1.0640. Min Range: -1.0640

Max Act: 0.8043. Min Act: -0.0001

Data Index: 1432928 (Python Code)

Max Activating Token Index: 257

Text #16

Max Range: 1.0640. Min Range: -1.0640

Max Act: 0.7938. Min Act: -0.0001

Data Index: 1430554 (Python Code)

Max Activating Token Index: 482

Text #17

Max Range: 1.0640. Min Range: -1.0640

Max Act: 0.7893. Min Act: -0.0001

Data Index: 1456653 (Python Code)

Max Activating Token Index: 82

Text #18

Max Range: 1.0640. Min Range: -1.0640

Max Act: 0.7632. Min Act: -0.0001

Data Index: 1448504 (Python Code)

Max Activating Token Index: 632

Text #19

Max Range: 1.0640. Min Range: -1.0640

Max Act: 0.8030. Min Act: -0.0001

Data Index: 1631617 (Python Code)

Max Activating Token Index: 136