Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 943 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.6094. Min Range: -4.6094

Max Act: 4.6094. Min Act: -0.0000

Data Index: 1067307 (C4 (Web Text))

Max Activating Token Index: 817

Text #1

Max Range: 4.6094. Min Range: -4.6094

Max Act: 4.2879. Min Act: -0.0000

Data Index: 1234267 (C4 (Web Text))

Max Activating Token Index: 176

Text #2

Max Range: 4.6094. Min Range: -4.6094

Max Act: 3.4423. Min Act: -0.0000

Data Index: 917975 (C4 (Web Text))

Max Activating Token Index: 970

Text #3

Max Range: 4.6094. Min Range: -4.6094

Max Act: 3.6137. Min Act: -0.0000

Data Index: 732016 (C4 (Web Text))

Max Activating Token Index: 464

Text #4

Max Range: 4.6094. Min Range: -4.6094

Max Act: 3.2045. Min Act: -0.0000

Data Index: 164933 (C4 (Web Text))

Max Activating Token Index: 216

Text #5

Max Range: 4.6094. Min Range: -4.6094

Max Act: 3.2979. Min Act: -0.0000

Data Index: 397338 (C4 (Web Text))

Max Activating Token Index: 696

Text #6

Max Range: 4.6094. Min Range: -4.6094

Max Act: 2.9081. Min Act: -0.0000

Data Index: 154560 (C4 (Web Text))

Max Activating Token Index: 940

Text #7

Max Range: 4.6094. Min Range: -4.6094

Max Act: 2.9759. Min Act: -0.0000

Data Index: 831756 (C4 (Web Text))

Max Activating Token Index: 785

Text #8

Max Range: 4.6094. Min Range: -4.6094

Max Act: 3.2028. Min Act: -0.0000

Data Index: 320202 (C4 (Web Text))

Max Activating Token Index: 407

Text #9

Max Range: 4.6094. Min Range: -4.6094

Max Act: 2.8900. Min Act: -0.0000

Data Index: 756703 (C4 (Web Text))

Max Activating Token Index: 110

Text #10

Max Range: 4.6094. Min Range: -4.6094

Max Act: 2.8336. Min Act: -0.0000

Data Index: 870545 (C4 (Web Text))

Max Activating Token Index: 171

Text #11

Max Range: 4.6094. Min Range: -4.6094

Max Act: 2.7755. Min Act: -0.0000

Data Index: 986530 (C4 (Web Text))

Max Activating Token Index: 532

Text #12

Max Range: 4.6094. Min Range: -4.6094

Max Act: 2.8748. Min Act: -0.0000

Data Index: 285942 (C4 (Web Text))

Max Activating Token Index: 366

Text #13

Max Range: 4.6094. Min Range: -4.6094

Max Act: 2.6880. Min Act: -0.0000

Data Index: 2842 (C4 (Web Text))

Max Activating Token Index: 204

Text #14

Max Range: 4.6094. Min Range: -4.6094

Max Act: 2.5483. Min Act: -0.0000

Data Index: 939672 (C4 (Web Text))

Max Activating Token Index: 35

Text #15

Max Range: 4.6094. Min Range: -4.6094

Max Act: 2.4614. Min Act: -0.0000

Data Index: 1309331 (C4 (Web Text))

Max Activating Token Index: 115

Text #16

Max Range: 4.6094. Min Range: -4.6094

Max Act: 2.4537. Min Act: -0.0000

Data Index: 846332 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 4.6094. Min Range: -4.6094

Max Act: 2.6935. Min Act: -0.0000

Data Index: 243001 (C4 (Web Text))

Max Activating Token Index: 715

Text #18

Max Range: 4.6094. Min Range: -4.6094

Max Act: 2.2992. Min Act: -0.0000

Data Index: 938815 (C4 (Web Text))

Max Activating Token Index: 84

Text #19

Max Range: 4.6094. Min Range: -4.6094

Max Act: 2.6601. Min Act: -0.0000

Data Index: 1229265 (C4 (Web Text))

Max Activating Token Index: 175