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

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

Neuron 2253 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9081. Min Range: -2.9081

Max Act: 2.9081. Min Act: -0.0001

Data Index: 1574491 (Python Code)

Max Activating Token Index: 123

Text #1

Max Range: 2.9081. Min Range: -2.9081

Max Act: 2.5099. Min Act: -0.0000

Data Index: 982516 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 2.9081. Min Range: -2.9081

Max Act: 2.6286. Min Act: -0.0000

Data Index: 854562 (C4 (Web Text))

Max Activating Token Index: 443

Text #3

Max Range: 2.9081. Min Range: -2.9081

Max Act: 2.4864. Min Act: -0.0000

Data Index: 361919 (C4 (Web Text))

Max Activating Token Index: 147

Text #4

Max Range: 2.9081. Min Range: -2.9081

Max Act: 2.6015. Min Act: -0.0000

Data Index: 1325011 (C4 (Web Text))

Max Activating Token Index: 225

Text #5

Max Range: 2.9081. Min Range: -2.9081

Max Act: 2.4576. Min Act: -0.0000

Data Index: 644444 (C4 (Web Text))

Max Activating Token Index: 717

Text #6

Max Range: 2.9081. Min Range: -2.9081

Max Act: 2.2971. Min Act: -0.0000

Data Index: 952588 (C4 (Web Text))

Max Activating Token Index: 981

Text #7

Max Range: 2.9081. Min Range: -2.9081

Max Act: 2.3420. Min Act: -0.0000

Data Index: 344261 (C4 (Web Text))

Max Activating Token Index: 147

Text #8

Max Range: 2.9081. Min Range: -2.9081

Max Act: 2.4485. Min Act: -0.0000

Data Index: 1321101 (C4 (Web Text))

Max Activating Token Index: 226

Text #9

Max Range: 2.9081. Min Range: -2.9081

Max Act: 2.2999. Min Act: -0.0001

Data Index: 1174372 (C4 (Web Text))

Max Activating Token Index: 70

Text #10

Max Range: 2.9081. Min Range: -2.9081

Max Act: 2.3024. Min Act: -0.0000

Data Index: 609972 (C4 (Web Text))

Max Activating Token Index: 441

Text #11

Max Range: 2.9081. Min Range: -2.9081

Max Act: 2.2865. Min Act: -0.0000

Data Index: 879751 (C4 (Web Text))

Max Activating Token Index: 362

Text #12

Max Range: 2.9081. Min Range: -2.9081

Max Act: 2.2642. Min Act: -0.0000

Data Index: 693155 (C4 (Web Text))

Max Activating Token Index: 931

Text #13

Max Range: 2.9081. Min Range: -2.9081

Max Act: 2.2517. Min Act: -0.0000

Data Index: 639033 (C4 (Web Text))

Max Activating Token Index: 547

Text #14

Max Range: 2.9081. Min Range: -2.9081

Max Act: 2.4023. Min Act: -0.0000

Data Index: 367602 (C4 (Web Text))

Max Activating Token Index: 264

Text #15

Max Range: 2.9081. Min Range: -2.9081

Max Act: 2.1415. Min Act: -0.0000

Data Index: 634088 (C4 (Web Text))

Max Activating Token Index: 842

Text #16

Max Range: 2.9081. Min Range: -2.9081

Max Act: 2.2204. Min Act: -0.0000

Data Index: 959260 (C4 (Web Text))

Max Activating Token Index: 126

Text #17

Max Range: 2.9081. Min Range: -2.9081

Max Act: 2.2122. Min Act: -0.0000

Data Index: 516879 (C4 (Web Text))

Max Activating Token Index: 425

Text #18

Max Range: 2.9081. Min Range: -2.9081

Max Act: 2.1998. Min Act: -0.0000

Data Index: 964274 (C4 (Web Text))

Max Activating Token Index: 859

Text #19

Max Range: 2.9081. Min Range: -2.9081

Max Act: 2.2021. Min Act: -0.0000

Data Index: 1314460 (C4 (Web Text))

Max Activating Token Index: 752