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

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

Neuron 376 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: 5.1993. Min Range: -5.1993

Max Act: 5.1993. Min Act: -0.0000

Data Index: 1109850 (C4 (Web Text))

Max Activating Token Index: 726

Text #1

Max Range: 5.1993. Min Range: -5.1993

Max Act: 5.1459. Min Act: -0.0001

Data Index: 695085 (C4 (Web Text))

Max Activating Token Index: 117

Text #2

Max Range: 5.1993. Min Range: -5.1993

Max Act: 4.9291. Min Act: -0.0000

Data Index: 911356 (C4 (Web Text))

Max Activating Token Index: 497

Text #3

Max Range: 5.1993. Min Range: -5.1993

Max Act: 4.5052. Min Act: -0.0001

Data Index: 77217 (C4 (Web Text))

Max Activating Token Index: 222

Text #4

Max Range: 5.1993. Min Range: -5.1993

Max Act: 4.7918. Min Act: -0.0001

Data Index: 656748 (C4 (Web Text))

Max Activating Token Index: 37

Text #5

Max Range: 5.1993. Min Range: -5.1993

Max Act: 4.6237. Min Act: -0.0001

Data Index: 520214 (C4 (Web Text))

Max Activating Token Index: 115

Text #6

Max Range: 5.1993. Min Range: -5.1993

Max Act: 4.7279. Min Act: -0.0001

Data Index: 396466 (C4 (Web Text))

Max Activating Token Index: 311

Text #7

Max Range: 5.1993. Min Range: -5.1993

Max Act: 4.7256. Min Act: -0.0001

Data Index: 1166688 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 5.1993. Min Range: -5.1993

Max Act: 4.6854. Min Act: -0.0001

Data Index: 1177566 (C4 (Web Text))

Max Activating Token Index: 350

Text #9

Max Range: 5.1993. Min Range: -5.1993

Max Act: 4.2824. Min Act: -0.0001

Data Index: 227547 (C4 (Web Text))

Max Activating Token Index: 69

Text #10

Max Range: 5.1993. Min Range: -5.1993

Max Act: 4.7935. Min Act: -0.0000

Data Index: 1003769 (C4 (Web Text))

Max Activating Token Index: 148

Text #11

Max Range: 5.1993. Min Range: -5.1993

Max Act: 4.7587. Min Act: -0.0001

Data Index: 58504 (C4 (Web Text))

Max Activating Token Index: 408

Text #12

Max Range: 5.1993. Min Range: -5.1993

Max Act: 4.5643. Min Act: -0.0001

Data Index: 1237622 (C4 (Web Text))

Max Activating Token Index: 116

Text #13

Max Range: 5.1993. Min Range: -5.1993

Max Act: 4.5678. Min Act: -0.0001

Data Index: 827105 (C4 (Web Text))

Max Activating Token Index: 980

Text #14

Max Range: 5.1993. Min Range: -5.1993

Max Act: 4.8381. Min Act: -0.0001

Data Index: 202842 (C4 (Web Text))

Max Activating Token Index: 247

Text #15

Max Range: 5.1993. Min Range: -5.1993

Max Act: 4.4867. Min Act: -0.0001

Data Index: 1099909 (C4 (Web Text))

Max Activating Token Index: 6

Text #16

Max Range: 5.1993. Min Range: -5.1993

Max Act: 4.2749. Min Act: -0.0000

Data Index: 1121971 (C4 (Web Text))

Max Activating Token Index: 363

Text #17

Max Range: 5.1993. Min Range: -5.1993

Max Act: 4.2793. Min Act: -0.0001

Data Index: 394040 (C4 (Web Text))

Max Activating Token Index: 133

Text #18

Max Range: 5.1993. Min Range: -5.1993

Max Act: 4.5827. Min Act: -0.0001

Data Index: 874583 (C4 (Web Text))

Max Activating Token Index: 11

Text #19

Max Range: 5.1993. Min Range: -5.1993

Max Act: 3.9377. Min Act: -0.0000

Data Index: 465536 (C4 (Web Text))

Max Activating Token Index: 966