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

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

Neuron 6042 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6954. Min Range: -4.6954

Max Act: 4.6954. Min Act: -0.0000

Data Index: 1287760 (C4 (Web Text))

Max Activating Token Index: 232

Text #1

Max Range: 4.6954. Min Range: -4.6954

Max Act: 4.0690. Min Act: -0.0000

Data Index: 453386 (C4 (Web Text))

Max Activating Token Index: 941

Text #2

Max Range: 4.6954. Min Range: -4.6954

Max Act: 2.3993. Min Act: 0.0000

Data Index: 1202937 (C4 (Web Text))

Max Activating Token Index: 189

Text #3

Max Range: 4.6954. Min Range: -4.6954

Max Act: 2.0860. Min Act: -0.0000

Data Index: 1159676 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 4.6954. Min Range: -4.6954

Max Act: 1.9895. Min Act: -0.0000

Data Index: 703130 (C4 (Web Text))

Max Activating Token Index: 827

Text #5

Max Range: 4.6954. Min Range: -4.6954

Max Act: 1.9327. Min Act: -0.0000

Data Index: 1308967 (C4 (Web Text))

Max Activating Token Index: 962

Text #6

Max Range: 4.6954. Min Range: -4.6954

Max Act: 2.1032. Min Act: -0.0000

Data Index: 264182 (C4 (Web Text))

Max Activating Token Index: 519

Text #7

Max Range: 4.6954. Min Range: -4.6954

Max Act: 1.9782. Min Act: -0.0000

Data Index: 1297261 (C4 (Web Text))

Max Activating Token Index: 836

Text #8

Max Range: 4.6954. Min Range: -4.6954

Max Act: 1.9051. Min Act: -0.0000

Data Index: 354956 (C4 (Web Text))

Max Activating Token Index: 791

Text #9

Max Range: 4.6954. Min Range: -4.6954

Max Act: 1.8656. Min Act: 0.0000

Data Index: 284219 (C4 (Web Text))

Max Activating Token Index: 585

Text #10

Max Range: 4.6954. Min Range: -4.6954

Max Act: 1.9678. Min Act: -0.0000

Data Index: 73716 (C4 (Web Text))

Max Activating Token Index: 107

Text #11

Max Range: 4.6954. Min Range: -4.6954

Max Act: 1.7563. Min Act: -0.0000

Data Index: 1225727 (C4 (Web Text))

Max Activating Token Index: 807

Text #12

Max Range: 4.6954. Min Range: -4.6954

Max Act: 1.8253. Min Act: -0.0000

Data Index: 393249 (C4 (Web Text))

Max Activating Token Index: 420

Text #13

Max Range: 4.6954. Min Range: -4.6954

Max Act: 1.8109. Min Act: -0.0000

Data Index: 298257 (C4 (Web Text))

Max Activating Token Index: 424

Text #14

Max Range: 4.6954. Min Range: -4.6954

Max Act: 1.7664. Min Act: -0.0000

Data Index: 345067 (C4 (Web Text))

Max Activating Token Index: 209

Text #15

Max Range: 4.6954. Min Range: -4.6954

Max Act: 1.7676. Min Act: -0.0000

Data Index: 236701 (C4 (Web Text))

Max Activating Token Index: 858

Text #16

Max Range: 4.6954. Min Range: -4.6954

Max Act: 1.7287. Min Act: -0.0000

Data Index: 1172495 (C4 (Web Text))

Max Activating Token Index: 711

Text #17

Max Range: 4.6954. Min Range: -4.6954

Max Act: 1.7202. Min Act: -0.0000

Data Index: 5669 (C4 (Web Text))

Max Activating Token Index: 40

Text #18

Max Range: 4.6954. Min Range: -4.6954

Max Act: 1.8151. Min Act: -0.0000

Data Index: 524050 (C4 (Web Text))

Max Activating Token Index: 167

Text #19

Max Range: 4.6954. Min Range: -4.6954

Max Act: 1.7926. Min Act: -0.0000

Data Index: 307264 (C4 (Web Text))

Max Activating Token Index: 942