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

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

Neuron 978 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4011. Min Range: -0.4011

Max Act: 0.4011. Min Act: -0.0001

Data Index: 1321871 (C4 (Web Text))

Max Activating Token Index: 945

Text #1

Max Range: 0.4011. Min Range: -0.4011

Max Act: 0.3530. Min Act: -0.0001

Data Index: 332076 (C4 (Web Text))

Max Activating Token Index: 647

Text #2

Max Range: 0.4011. Min Range: -0.4011

Max Act: 0.3404. Min Act: -0.0001

Data Index: 1067307 (C4 (Web Text))

Max Activating Token Index: 576

Text #3

Max Range: 0.4011. Min Range: -0.4011

Max Act: 0.3384. Min Act: -0.0001

Data Index: 506209 (C4 (Web Text))

Max Activating Token Index: 86

Text #4

Max Range: 0.4011. Min Range: -0.4011

Max Act: 0.3350. Min Act: -0.0001

Data Index: 375005 (C4 (Web Text))

Max Activating Token Index: 748

Text #5

Max Range: 0.4011. Min Range: -0.4011

Max Act: 0.2853. Min Act: -0.0001

Data Index: 748669 (C4 (Web Text))

Max Activating Token Index: 852

Text #6

Max Range: 0.4011. Min Range: -0.4011

Max Act: 0.3143. Min Act: -0.0001

Data Index: 342219 (C4 (Web Text))

Max Activating Token Index: 805

Text #7

Max Range: 0.4011. Min Range: -0.4011

Max Act: 0.3037. Min Act: -0.0001

Data Index: 1140354 (C4 (Web Text))

Max Activating Token Index: 898

Text #8

Max Range: 0.4011. Min Range: -0.4011

Max Act: 0.3103. Min Act: -0.0001

Data Index: 305444 (C4 (Web Text))

Max Activating Token Index: 39

Text #9

Max Range: 0.4011. Min Range: -0.4011

Max Act: 0.2727. Min Act: -0.0001

Data Index: 199777 (C4 (Web Text))

Max Activating Token Index: 791

Text #10

Max Range: 0.4011. Min Range: -0.4011

Max Act: 0.2991. Min Act: -0.0001

Data Index: 963475 (C4 (Web Text))

Max Activating Token Index: 330

Text #11

Max Range: 0.4011. Min Range: -0.4011

Max Act: 0.2889. Min Act: -0.0001

Data Index: 293879 (C4 (Web Text))

Max Activating Token Index: 166

Text #12

Max Range: 0.4011. Min Range: -0.4011

Max Act: 0.2868. Min Act: -0.0001

Data Index: 131418 (C4 (Web Text))

Max Activating Token Index: 196

Text #13

Max Range: 0.4011. Min Range: -0.4011

Max Act: 0.2757. Min Act: -0.0001

Data Index: 632522 (C4 (Web Text))

Max Activating Token Index: 697

Text #14

Max Range: 0.4011. Min Range: -0.4011

Max Act: 0.2820. Min Act: -0.0001

Data Index: 888314 (C4 (Web Text))

Max Activating Token Index: 953

Text #15

Max Range: 0.4011. Min Range: -0.4011

Max Act: 0.2802. Min Act: -0.0001

Data Index: 248010 (C4 (Web Text))

Max Activating Token Index: 227

Text #16

Max Range: 0.4011. Min Range: -0.4011

Max Act: 0.2786. Min Act: -0.0001

Data Index: 1036915 (C4 (Web Text))

Max Activating Token Index: 107

Text #17

Max Range: 0.4011. Min Range: -0.4011

Max Act: 0.2669. Min Act: -0.0001

Data Index: 789711 (C4 (Web Text))

Max Activating Token Index: 988

Text #18

Max Range: 0.4011. Min Range: -0.4011

Max Act: 0.2740. Min Act: -0.0001

Data Index: 292562 (C4 (Web Text))

Max Activating Token Index: 990

Text #19

Max Range: 0.4011. Min Range: -0.4011

Max Act: 0.2750. Min Act: -0.0001

Data Index: 1048076 (C4 (Web Text))

Max Activating Token Index: 899