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

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

Neuron 1749 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1935. Min Range: -1.1935

Max Act: 1.1695. Min Act: -0.0001

Data Index: 1545161 (Python Code)

Max Activating Token Index: 209

Text #1

Max Range: 1.1935. Min Range: -1.1935

Max Act: 1.1935. Min Act: -0.0001

Data Index: 1557942 (Python Code)

Max Activating Token Index: 871

Text #2

Max Range: 1.1935. Min Range: -1.1935

Max Act: 1.0518. Min Act: -0.0001

Data Index: 1617795 (Python Code)

Max Activating Token Index: 190

Text #3

Max Range: 1.1935. Min Range: -1.1935

Max Act: 0.9752. Min Act: -0.0001

Data Index: 1624086 (Python Code)

Max Activating Token Index: 387

Text #4

Max Range: 1.1935. Min Range: -1.1935

Max Act: 0.8933. Min Act: -0.0001

Data Index: 1525376 (Python Code)

Max Activating Token Index: 599

Text #5

Max Range: 1.1935. Min Range: -1.1935

Max Act: 0.8849. Min Act: -0.0001

Data Index: 1486769 (Python Code)

Max Activating Token Index: 980

Text #6

Max Range: 1.1935. Min Range: -1.1935

Max Act: 0.8878. Min Act: -0.0001

Data Index: 1445056 (Python Code)

Max Activating Token Index: 811

Text #7

Max Range: 1.1935. Min Range: -1.1935

Max Act: 0.9016. Min Act: -0.0001

Data Index: 1520087 (Python Code)

Max Activating Token Index: 82

Text #8

Max Range: 1.1935. Min Range: -1.1935

Max Act: 0.8257. Min Act: -0.0001

Data Index: 1650777 (Python Code)

Max Activating Token Index: 372

Text #9

Max Range: 1.1935. Min Range: -1.1935

Max Act: 0.8188. Min Act: -0.0001

Data Index: 1578257 (Python Code)

Max Activating Token Index: 479

Text #10

Max Range: 1.1935. Min Range: -1.1935

Max Act: 0.8153. Min Act: -0.0001

Data Index: 1498130 (Python Code)

Max Activating Token Index: 259

Text #11

Max Range: 1.1935. Min Range: -1.1935

Max Act: 0.8607. Min Act: -0.0001

Data Index: 1526052 (Python Code)

Max Activating Token Index: 528

Text #12

Max Range: 1.1935. Min Range: -1.1935

Max Act: 0.8337. Min Act: -0.0001

Data Index: 1623018 (Python Code)

Max Activating Token Index: 608

Text #13

Max Range: 1.1935. Min Range: -1.1935

Max Act: 0.7180. Min Act: -0.0001

Data Index: 1638545 (Python Code)

Max Activating Token Index: 616

Text #14

Max Range: 1.1935. Min Range: -1.1935

Max Act: 0.8624. Min Act: -0.0001

Data Index: 1397124 (Python Code)

Max Activating Token Index: 249

Text #15

Max Range: 1.1935. Min Range: -1.1935

Max Act: 0.8291. Min Act: -0.0001

Data Index: 1554493 (Python Code)

Max Activating Token Index: 91

Text #16

Max Range: 1.1935. Min Range: -1.1935

Max Act: 0.8305. Min Act: -0.0001

Data Index: 1445645 (Python Code)

Max Activating Token Index: 277

Text #17

Max Range: 1.1935. Min Range: -1.1935

Max Act: 0.7186. Min Act: -0.0001

Data Index: 1535018 (Python Code)

Max Activating Token Index: 181

Text #18

Max Range: 1.1935. Min Range: -1.1935

Max Act: 0.7880. Min Act: -0.0001

Data Index: 1467798 (Python Code)

Max Activating Token Index: 525

Text #19

Max Range: 1.1935. Min Range: -1.1935

Max Act: 0.7360. Min Act: -0.0001

Data Index: 1476992 (Python Code)

Max Activating Token Index: 874