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

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

Neuron 2948 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: 0.5921. Min Range: -0.5921

Max Act: 0.5921. Min Act: -0.0000

Data Index: 1234405 (C4 (Web Text))

Max Activating Token Index: 573

Text #1

Max Range: 0.5921. Min Range: -0.5921

Max Act: 0.4979. Min Act: -0.0000

Data Index: 995573 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 0.5921. Min Range: -0.5921

Max Act: 0.4294. Min Act: -0.0000

Data Index: 886757 (C4 (Web Text))

Max Activating Token Index: 154

Text #3

Max Range: 0.5921. Min Range: -0.5921

Max Act: 0.4249. Min Act: -0.0001

Data Index: 602136 (C4 (Web Text))

Max Activating Token Index: 525

Text #4

Max Range: 0.5921. Min Range: -0.5921

Max Act: 0.4322. Min Act: -0.0000

Data Index: 938369 (C4 (Web Text))

Max Activating Token Index: 186

Text #5

Max Range: 0.5921. Min Range: -0.5921

Max Act: 0.4022. Min Act: -0.0000

Data Index: 443254 (C4 (Web Text))

Max Activating Token Index: 797

Text #6

Max Range: 0.5921. Min Range: -0.5921

Max Act: 0.4014. Min Act: -0.0000

Data Index: 142557 (C4 (Web Text))

Max Activating Token Index: 269

Text #7

Max Range: 0.5921. Min Range: -0.5921

Max Act: 0.4098. Min Act: -0.0000

Data Index: 1107256 (C4 (Web Text))

Max Activating Token Index: 368

Text #8

Max Range: 0.5921. Min Range: -0.5921

Max Act: 0.4074. Min Act: -0.0000

Data Index: 1122538 (C4 (Web Text))

Max Activating Token Index: 283

Text #9

Max Range: 0.5921. Min Range: -0.5921

Max Act: 0.4061. Min Act: -0.0001

Data Index: 435143 (C4 (Web Text))

Max Activating Token Index: 215

Text #10

Max Range: 0.5921. Min Range: -0.5921

Max Act: 0.4052. Min Act: -0.0000

Data Index: 687744 (C4 (Web Text))

Max Activating Token Index: 311

Text #11

Max Range: 0.5921. Min Range: -0.5921

Max Act: 0.4214. Min Act: -0.0001

Data Index: 137525 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 0.5921. Min Range: -0.5921

Max Act: 0.3761. Min Act: -0.0000

Data Index: 254667 (C4 (Web Text))

Max Activating Token Index: 229

Text #13

Max Range: 0.5921. Min Range: -0.5921

Max Act: 0.4104. Min Act: -0.0000

Data Index: 641152 (C4 (Web Text))

Max Activating Token Index: 856

Text #14

Max Range: 0.5921. Min Range: -0.5921

Max Act: 0.3808. Min Act: -0.0001

Data Index: 961 (C4 (Web Text))

Max Activating Token Index: 733

Text #15

Max Range: 0.5921. Min Range: -0.5921

Max Act: 0.3773. Min Act: -0.0000

Data Index: 948677 (C4 (Web Text))

Max Activating Token Index: 797

Text #16

Max Range: 0.5921. Min Range: -0.5921

Max Act: 0.3924. Min Act: -0.0000

Data Index: 776007 (C4 (Web Text))

Max Activating Token Index: 5

Text #17

Max Range: 0.5921. Min Range: -0.5921

Max Act: 0.4038. Min Act: -0.0000

Data Index: 908571 (C4 (Web Text))

Max Activating Token Index: 8

Text #18

Max Range: 0.5921. Min Range: -0.5921

Max Act: 0.3880. Min Act: -0.0000

Data Index: 221512 (C4 (Web Text))

Max Activating Token Index: 190

Text #19

Max Range: 0.5921. Min Range: -0.5921

Max Act: 0.3767. Min Act: -0.0000

Data Index: 1013609 (C4 (Web Text))

Max Activating Token Index: 102