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

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

Neuron 3166 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6303. Min Range: -1.6303

Max Act: 1.6303. Min Act: -0.0001

Data Index: 560087 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 1.6303. Min Range: -1.6303

Max Act: 1.3934. Min Act: -0.0001

Data Index: 1059948 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 1.6303. Min Range: -1.6303

Max Act: 1.4394. Min Act: -0.0001

Data Index: 548164 (C4 (Web Text))

Max Activating Token Index: 968

Text #3

Max Range: 1.6303. Min Range: -1.6303

Max Act: 1.3607. Min Act: -0.0001

Data Index: 900226 (C4 (Web Text))

Max Activating Token Index: 11

Text #4

Max Range: 1.6303. Min Range: -1.6303

Max Act: 1.2769. Min Act: -0.0001

Data Index: 225221 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 1.6303. Min Range: -1.6303

Max Act: 1.2742. Min Act: -0.0001

Data Index: 440860 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 1.6303. Min Range: -1.6303

Max Act: 1.3504. Min Act: -0.0001

Data Index: 357748 (C4 (Web Text))

Max Activating Token Index: 971

Text #7

Max Range: 1.6303. Min Range: -1.6303

Max Act: 1.1146. Min Act: -0.0001

Data Index: 89837 (C4 (Web Text))

Max Activating Token Index: 255

Text #8

Max Range: 1.6303. Min Range: -1.6303

Max Act: 1.1105. Min Act: -0.0001

Data Index: 54785 (C4 (Web Text))

Max Activating Token Index: 22

Text #9

Max Range: 1.6303. Min Range: -1.6303

Max Act: 1.1341. Min Act: -0.0001

Data Index: 487248 (C4 (Web Text))

Max Activating Token Index: 124

Text #10

Max Range: 1.6303. Min Range: -1.6303

Max Act: 1.1410. Min Act: -0.0001

Data Index: 660086 (C4 (Web Text))

Max Activating Token Index: 14

Text #11

Max Range: 1.6303. Min Range: -1.6303

Max Act: 1.1199. Min Act: -0.0001

Data Index: 129165 (C4 (Web Text))

Max Activating Token Index: 31

Text #12

Max Range: 1.6303. Min Range: -1.6303

Max Act: 0.9787. Min Act: -0.0001

Data Index: 63487 (C4 (Web Text))

Max Activating Token Index: 822

Text #13

Max Range: 1.6303. Min Range: -1.6303

Max Act: 1.0423. Min Act: -0.0001

Data Index: 1176125 (C4 (Web Text))

Max Activating Token Index: 525

Text #14

Max Range: 1.6303. Min Range: -1.6303

Max Act: 0.9850. Min Act: -0.0001

Data Index: 583256 (C4 (Web Text))

Max Activating Token Index: 17

Text #15

Max Range: 1.6303. Min Range: -1.6303

Max Act: 1.0244. Min Act: -0.0001

Data Index: 289535 (C4 (Web Text))

Max Activating Token Index: 876

Text #16

Max Range: 1.6303. Min Range: -1.6303

Max Act: 0.8963. Min Act: -0.0001

Data Index: 35655 (C4 (Web Text))

Max Activating Token Index: 225

Text #17

Max Range: 1.6303. Min Range: -1.6303

Max Act: 1.0228. Min Act: -0.0001

Data Index: 688763 (C4 (Web Text))

Max Activating Token Index: 128

Text #18

Max Range: 1.6303. Min Range: -1.6303

Max Act: 0.9735. Min Act: -0.0001

Data Index: 596378 (C4 (Web Text))

Max Activating Token Index: 340

Text #19

Max Range: 1.6303. Min Range: -1.6303

Max Act: 0.9823. Min Act: -0.0001

Data Index: 367407 (C4 (Web Text))

Max Activating Token Index: 895