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

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

Neuron 4191 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1021. Min Act: -0.0001

Data Index: 751239 (C4 (Web Text))

Max Activating Token Index: 171

Text #1

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1051. Min Act: -0.0001

Data Index: 76971 (C4 (Web Text))

Max Activating Token Index: 71

Text #2

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1141. Min Act: -0.0001

Data Index: 34555 (C4 (Web Text))

Max Activating Token Index: 822

Text #3

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0956. Min Act: -0.0001

Data Index: 779376 (C4 (Web Text))

Max Activating Token Index: 409

Text #4

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0967. Min Act: -0.0001

Data Index: 1272790 (C4 (Web Text))

Max Activating Token Index: 357

Text #5

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0960. Min Act: -0.0001

Data Index: 1058901 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0922. Min Act: -0.0001

Data Index: 912581 (C4 (Web Text))

Max Activating Token Index: 698

Text #7

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0924. Min Act: -0.0001

Data Index: 726454 (C4 (Web Text))

Max Activating Token Index: 212

Text #8

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0904. Min Act: -0.0001

Data Index: 3539 (C4 (Web Text))

Max Activating Token Index: 76

Text #9

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0936. Min Act: -0.0001

Data Index: 1135439 (C4 (Web Text))

Max Activating Token Index: 101

Text #10

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0900. Min Act: -0.0001

Data Index: 1124075 (C4 (Web Text))

Max Activating Token Index: 334

Text #11

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0870. Min Act: -0.0001

Data Index: 367663 (C4 (Web Text))

Max Activating Token Index: 932

Text #12

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0929. Min Act: -0.0001

Data Index: 515444 (C4 (Web Text))

Max Activating Token Index: 131

Text #13

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0892. Min Act: -0.0001

Data Index: 253006 (C4 (Web Text))

Max Activating Token Index: 977

Text #14

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0916. Min Act: -0.0001

Data Index: 1328359 (C4 (Web Text))

Max Activating Token Index: 947

Text #15

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0881. Min Act: -0.0001

Data Index: 868144 (C4 (Web Text))

Max Activating Token Index: 154

Text #16

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0900. Min Act: -0.0001

Data Index: 475404 (C4 (Web Text))

Max Activating Token Index: 87

Text #17

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0858. Min Act: -0.0001

Data Index: 363985 (C4 (Web Text))

Max Activating Token Index: 374

Text #18

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0825. Min Act: -0.0001

Data Index: 219978 (C4 (Web Text))

Max Activating Token Index: 875

Text #19

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0815. Min Act: -0.0001

Data Index: 233112 (C4 (Web Text))

Max Activating Token Index: 308