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

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

Neuron 1531 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5038. Min Range: -3.5038

Max Act: 3.5038. Min Act: -0.0001

Data Index: 343550 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 3.5038. Min Range: -3.5038

Max Act: 2.9295. Min Act: -0.0001

Data Index: 603549 (C4 (Web Text))

Max Activating Token Index: 850

Text #2

Max Range: 3.5038. Min Range: -3.5038

Max Act: 3.2728. Min Act: -0.0001

Data Index: 285225 (C4 (Web Text))

Max Activating Token Index: 518

Text #3

Max Range: 3.5038. Min Range: -3.5038

Max Act: 3.2489. Min Act: -0.0001

Data Index: 321132 (C4 (Web Text))

Max Activating Token Index: 326

Text #4

Max Range: 3.5038. Min Range: -3.5038

Max Act: 3.4803. Min Act: -0.0001

Data Index: 1124050 (C4 (Web Text))

Max Activating Token Index: 816

Text #5

Max Range: 3.5038. Min Range: -3.5038

Max Act: 3.4756. Min Act: -0.0001

Data Index: 1072359 (C4 (Web Text))

Max Activating Token Index: 584

Text #6

Max Range: 3.5038. Min Range: -3.5038

Max Act: 2.9342. Min Act: -0.0001

Data Index: 871896 (C4 (Web Text))

Max Activating Token Index: 854

Text #7

Max Range: 3.5038. Min Range: -3.5038

Max Act: 3.2627. Min Act: -0.0001

Data Index: 416675 (C4 (Web Text))

Max Activating Token Index: 25

Text #8

Max Range: 3.5038. Min Range: -3.5038

Max Act: 2.9033. Min Act: -0.0001

Data Index: 1048989 (C4 (Web Text))

Max Activating Token Index: 353

Text #9

Max Range: 3.5038. Min Range: -3.5038

Max Act: 2.8421. Min Act: -0.0001

Data Index: 679177 (C4 (Web Text))

Max Activating Token Index: 220

Text #10

Max Range: 3.5038. Min Range: -3.5038

Max Act: 3.2083. Min Act: -0.0001

Data Index: 187673 (C4 (Web Text))

Max Activating Token Index: 105

Text #11

Max Range: 3.5038. Min Range: -3.5038

Max Act: 3.0510. Min Act: -0.0001

Data Index: 406085 (C4 (Web Text))

Max Activating Token Index: 190

Text #12

Max Range: 3.5038. Min Range: -3.5038

Max Act: 3.1258. Min Act: -0.0001

Data Index: 573992 (C4 (Web Text))

Max Activating Token Index: 56

Text #13

Max Range: 3.5038. Min Range: -3.5038

Max Act: 2.8839. Min Act: -0.0001

Data Index: 33070 (C4 (Web Text))

Max Activating Token Index: 304

Text #14

Max Range: 3.5038. Min Range: -3.5038

Max Act: 2.8337. Min Act: -0.0001

Data Index: 365090 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 3.5038. Min Range: -3.5038

Max Act: 2.9624. Min Act: -0.0001

Data Index: 354258 (C4 (Web Text))

Max Activating Token Index: 290

Text #16

Max Range: 3.5038. Min Range: -3.5038

Max Act: 3.1072. Min Act: -0.0001

Data Index: 133858 (C4 (Web Text))

Max Activating Token Index: 247

Text #17

Max Range: 3.5038. Min Range: -3.5038

Max Act: 2.9862. Min Act: -0.0001

Data Index: 505850 (C4 (Web Text))

Max Activating Token Index: 414

Text #18

Max Range: 3.5038. Min Range: -3.5038

Max Act: 3.0470. Min Act: -0.0001

Data Index: 923004 (C4 (Web Text))

Max Activating Token Index: 698

Text #19

Max Range: 3.5038. Min Range: -3.5038

Max Act: 3.0532. Min Act: -0.0001

Data Index: 966154 (C4 (Web Text))

Max Activating Token Index: 899