Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 318 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9193. Min Range: -0.9193

Max Act: 0.9193. Min Act: -0.0001

Data Index: 603819 (C4 (Web Text))

Max Activating Token Index: 108

Text #1

Max Range: 0.9193. Min Range: -0.9193

Max Act: 0.8848. Min Act: -0.0001

Data Index: 909133 (C4 (Web Text))

Max Activating Token Index: 80

Text #2

Max Range: 0.9193. Min Range: -0.9193

Max Act: 0.8611. Min Act: -0.0001

Data Index: 772568 (C4 (Web Text))

Max Activating Token Index: 474

Text #3

Max Range: 0.9193. Min Range: -0.9193

Max Act: 0.8302. Min Act: -0.0001

Data Index: 819087 (C4 (Web Text))

Max Activating Token Index: 737

Text #4

Max Range: 0.9193. Min Range: -0.9193

Max Act: 0.8072. Min Act: -0.0001

Data Index: 899750 (C4 (Web Text))

Max Activating Token Index: 834

Text #5

Max Range: 0.9193. Min Range: -0.9193

Max Act: 0.7992. Min Act: -0.0001

Data Index: 1160969 (C4 (Web Text))

Max Activating Token Index: 407

Text #6

Max Range: 0.9193. Min Range: -0.9193

Max Act: 0.8223. Min Act: -0.0001

Data Index: 104557 (C4 (Web Text))

Max Activating Token Index: 209

Text #7

Max Range: 0.9193. Min Range: -0.9193

Max Act: 0.8170. Min Act: -0.0001

Data Index: 214809 (C4 (Web Text))

Max Activating Token Index: 492

Text #8

Max Range: 0.9193. Min Range: -0.9193

Max Act: 0.8386. Min Act: -0.0001

Data Index: 39578 (C4 (Web Text))

Max Activating Token Index: 935

Text #9

Max Range: 0.9193. Min Range: -0.9193

Max Act: 0.7732. Min Act: -0.0001

Data Index: 62563 (C4 (Web Text))

Max Activating Token Index: 165

Text #10

Max Range: 0.9193. Min Range: -0.9193

Max Act: 0.8006. Min Act: -0.0001

Data Index: 1028110 (C4 (Web Text))

Max Activating Token Index: 310

Text #11

Max Range: 0.9193. Min Range: -0.9193

Max Act: 0.7758. Min Act: -0.0001

Data Index: 915793 (C4 (Web Text))

Max Activating Token Index: 938

Text #12

Max Range: 0.9193. Min Range: -0.9193

Max Act: 0.7912. Min Act: -0.0001

Data Index: 360915 (C4 (Web Text))

Max Activating Token Index: 194

Text #13

Max Range: 0.9193. Min Range: -0.9193

Max Act: 0.7983. Min Act: -0.0001

Data Index: 20010 (C4 (Web Text))

Max Activating Token Index: 98

Text #14

Max Range: 0.9193. Min Range: -0.9193

Max Act: 0.7647. Min Act: -0.0001

Data Index: 784778 (C4 (Web Text))

Max Activating Token Index: 533

Text #15

Max Range: 0.9193. Min Range: -0.9193

Max Act: 0.8090. Min Act: -0.0001

Data Index: 678119 (C4 (Web Text))

Max Activating Token Index: 817

Text #16

Max Range: 0.9193. Min Range: -0.9193

Max Act: 0.7780. Min Act: -0.0001

Data Index: 664404 (C4 (Web Text))

Max Activating Token Index: 871

Text #17

Max Range: 0.9193. Min Range: -0.9193

Max Act: 0.7848. Min Act: -0.0001

Data Index: 258663 (C4 (Web Text))

Max Activating Token Index: 532

Text #18

Max Range: 0.9193. Min Range: -0.9193

Max Act: 0.8101. Min Act: -0.0001

Data Index: 278997 (C4 (Web Text))

Max Activating Token Index: 110

Text #19

Max Range: 0.9193. Min Range: -0.9193

Max Act: 0.7561. Min Act: -0.0001

Data Index: 125573 (C4 (Web Text))

Max Activating Token Index: 48