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

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

Neuron 2918 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: 0.6008. Min Range: -0.6008

Max Act: 0.6008. Min Act: -0.0002

Data Index: 341455 (C4 (Web Text))

Max Activating Token Index: 716

Text #1

Max Range: 0.6008. Min Range: -0.6008

Max Act: 0.5641. Min Act: -0.0002

Data Index: 865064 (C4 (Web Text))

Max Activating Token Index: 236

Text #2

Max Range: 0.6008. Min Range: -0.6008

Max Act: 0.5642. Min Act: -0.0002

Data Index: 1025355 (C4 (Web Text))

Max Activating Token Index: 646

Text #3

Max Range: 0.6008. Min Range: -0.6008

Max Act: 0.5272. Min Act: -0.0002

Data Index: 315110 (C4 (Web Text))

Max Activating Token Index: 1010

Text #4

Max Range: 0.6008. Min Range: -0.6008

Max Act: 0.5322. Min Act: -0.0001

Data Index: 1083119 (C4 (Web Text))

Max Activating Token Index: 692

Text #5

Max Range: 0.6008. Min Range: -0.6008

Max Act: 0.5125. Min Act: -0.0002

Data Index: 1035420 (C4 (Web Text))

Max Activating Token Index: 20

Text #6

Max Range: 0.6008. Min Range: -0.6008

Max Act: 0.5031. Min Act: -0.0001

Data Index: 224246 (C4 (Web Text))

Max Activating Token Index: 809

Text #7

Max Range: 0.6008. Min Range: -0.6008

Max Act: 0.4853. Min Act: -0.0002

Data Index: 967690 (C4 (Web Text))

Max Activating Token Index: 973

Text #8

Max Range: 0.6008. Min Range: -0.6008

Max Act: 0.4789. Min Act: -0.0002

Data Index: 357940 (C4 (Web Text))

Max Activating Token Index: 108

Text #9

Max Range: 0.6008. Min Range: -0.6008

Max Act: 0.4915. Min Act: -0.0002

Data Index: 212126 (C4 (Web Text))

Max Activating Token Index: 757

Text #10

Max Range: 0.6008. Min Range: -0.6008

Max Act: 0.4939. Min Act: -0.0002

Data Index: 20452 (C4 (Web Text))

Max Activating Token Index: 90

Text #11

Max Range: 0.6008. Min Range: -0.6008

Max Act: 0.4913. Min Act: -0.0002

Data Index: 776976 (C4 (Web Text))

Max Activating Token Index: 944

Text #12

Max Range: 0.6008. Min Range: -0.6008

Max Act: 0.5057. Min Act: -0.0002

Data Index: 882177 (C4 (Web Text))

Max Activating Token Index: 269

Text #13

Max Range: 0.6008. Min Range: -0.6008

Max Act: 0.5135. Min Act: -0.0002

Data Index: 1201374 (C4 (Web Text))

Max Activating Token Index: 98

Text #14

Max Range: 0.6008. Min Range: -0.6008

Max Act: 0.4990. Min Act: -0.0002

Data Index: 899471 (C4 (Web Text))

Max Activating Token Index: 7

Text #15

Max Range: 0.6008. Min Range: -0.6008

Max Act: 0.5147. Min Act: -0.0002

Data Index: 369258 (C4 (Web Text))

Max Activating Token Index: 112

Text #16

Max Range: 0.6008. Min Range: -0.6008

Max Act: 0.4635. Min Act: -0.0002

Data Index: 208544 (C4 (Web Text))

Max Activating Token Index: 1020

Text #17

Max Range: 0.6008. Min Range: -0.6008

Max Act: 0.4773. Min Act: -0.0002

Data Index: 1174542 (C4 (Web Text))

Max Activating Token Index: 117

Text #18

Max Range: 0.6008. Min Range: -0.6008

Max Act: 0.4916. Min Act: -0.0002

Data Index: 535048 (C4 (Web Text))

Max Activating Token Index: 414

Text #19

Max Range: 0.6008. Min Range: -0.6008

Max Act: 0.4874. Min Act: -0.0002

Data Index: 438084 (C4 (Web Text))

Max Activating Token Index: 460