Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 3039 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0972. Min Act: -0.0001

Data Index: 1088578 (C4 (Web Text))

Max Activating Token Index: 209

Text #1

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0952. Min Act: -0.0001

Data Index: 1071658 (C4 (Web Text))

Max Activating Token Index: 98

Text #2

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0882. Min Act: -0.0001

Data Index: 557526 (C4 (Web Text))

Max Activating Token Index: 611

Text #3

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0920. Min Act: -0.0001

Data Index: 177763 (C4 (Web Text))

Max Activating Token Index: 505

Text #4

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0921. Min Act: -0.0001

Data Index: 1293340 (C4 (Web Text))

Max Activating Token Index: 456

Text #5

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0947. Min Act: -0.0001

Data Index: 316789 (C4 (Web Text))

Max Activating Token Index: 148

Text #6

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0929. Min Act: -0.0001

Data Index: 1308178 (C4 (Web Text))

Max Activating Token Index: 473

Text #7

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0939. Min Act: -0.0001

Data Index: 3567 (C4 (Web Text))

Max Activating Token Index: 235

Text #8

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0926. Min Act: -0.0001

Data Index: 252784 (C4 (Web Text))

Max Activating Token Index: 176

Text #9

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0911. Min Act: -0.0001

Data Index: 74845 (C4 (Web Text))

Max Activating Token Index: 361

Text #10

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0927. Min Act: -0.0001

Data Index: 76624 (C4 (Web Text))

Max Activating Token Index: 155

Text #11

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0918. Min Act: -0.0001

Data Index: 179617 (C4 (Web Text))

Max Activating Token Index: 148

Text #12

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0915. Min Act: -0.0001

Data Index: 725776 (C4 (Web Text))

Max Activating Token Index: 100

Text #13

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0896. Min Act: -0.0001

Data Index: 463124 (C4 (Web Text))

Max Activating Token Index: 29

Text #14

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0942. Min Act: -0.0001

Data Index: 229263 (C4 (Web Text))

Max Activating Token Index: 125

Text #15

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0912. Min Act: -0.0001

Data Index: 1174077 (C4 (Web Text))

Max Activating Token Index: 320

Text #16

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0907. Min Act: -0.0001

Data Index: 542166 (C4 (Web Text))

Max Activating Token Index: 118

Text #17

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0913. Min Act: -0.0001

Data Index: 410620 (C4 (Web Text))

Max Activating Token Index: 577

Text #18

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0899. Min Act: -0.0001

Data Index: 1184440 (C4 (Web Text))

Max Activating Token Index: 61

Text #19

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0921. Min Act: -0.0001

Data Index: 73209 (C4 (Web Text))

Max Activating Token Index: 573