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

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

Neuron 2085 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: 0.4950. Min Range: -0.4950

Max Act: 0.4950. Min Act: -0.0001

Data Index: 1285611 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.4460. Min Act: -0.0001

Data Index: 953928 (C4 (Web Text))

Max Activating Token Index: 49

Text #2

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.3732. Min Act: -0.0001

Data Index: 937525 (C4 (Web Text))

Max Activating Token Index: 790

Text #3

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.4188. Min Act: -0.0001

Data Index: 237171 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.4179. Min Act: -0.0001

Data Index: 996094 (C4 (Web Text))

Max Activating Token Index: 92

Text #5

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.3965. Min Act: -0.0001

Data Index: 618550 (C4 (Web Text))

Max Activating Token Index: 146

Text #6

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.3837. Min Act: -0.0001

Data Index: 331097 (C4 (Web Text))

Max Activating Token Index: 141

Text #7

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.4149. Min Act: -0.0001

Data Index: 1032509 (C4 (Web Text))

Max Activating Token Index: 310

Text #8

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.4247. Min Act: -0.0001

Data Index: 1387 (C4 (Web Text))

Max Activating Token Index: 119

Text #9

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.3808. Min Act: -0.0001

Data Index: 319563 (C4 (Web Text))

Max Activating Token Index: 65

Text #10

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.4028. Min Act: -0.0001

Data Index: 580760 (C4 (Web Text))

Max Activating Token Index: 491

Text #11

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.4147. Min Act: -0.0001

Data Index: 1094719 (C4 (Web Text))

Max Activating Token Index: 309

Text #12

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.4154. Min Act: -0.0001

Data Index: 177218 (C4 (Web Text))

Max Activating Token Index: 53

Text #13

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.3914. Min Act: -0.0001

Data Index: 1254664 (C4 (Web Text))

Max Activating Token Index: 699

Text #14

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.3709. Min Act: -0.0001

Data Index: 233407 (C4 (Web Text))

Max Activating Token Index: 972

Text #15

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.3751. Min Act: -0.0001

Data Index: 103289 (C4 (Web Text))

Max Activating Token Index: 701

Text #16

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.3692. Min Act: -0.0001

Data Index: 1169225 (C4 (Web Text))

Max Activating Token Index: 350

Text #17

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.3957. Min Act: -0.0001

Data Index: 409856 (C4 (Web Text))

Max Activating Token Index: 947

Text #18

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.3944. Min Act: -0.0001

Data Index: 638571 (C4 (Web Text))

Max Activating Token Index: 492

Text #19

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.3798. Min Act: -0.0001

Data Index: 58214 (C4 (Web Text))

Max Activating Token Index: 125