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

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

Neuron 1854 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0597. Min Range: -5.0597

Max Act: 5.0597. Min Act: -0.0000

Data Index: 232837 (C4 (Web Text))

Max Activating Token Index: 670

Text #1

Max Range: 5.0597. Min Range: -5.0597

Max Act: 4.4367. Min Act: -0.0000

Data Index: 923788 (C4 (Web Text))

Max Activating Token Index: 583

Text #2

Max Range: 5.0597. Min Range: -5.0597

Max Act: 4.5410. Min Act: -0.0000

Data Index: 683922 (C4 (Web Text))

Max Activating Token Index: 813

Text #3

Max Range: 5.0597. Min Range: -5.0597

Max Act: 4.3034. Min Act: -0.0000

Data Index: 1018180 (C4 (Web Text))

Max Activating Token Index: 867

Text #4

Max Range: 5.0597. Min Range: -5.0597

Max Act: 4.2591. Min Act: -0.0000

Data Index: 1003830 (C4 (Web Text))

Max Activating Token Index: 126

Text #5

Max Range: 5.0597. Min Range: -5.0597

Max Act: 4.0502. Min Act: -0.0000

Data Index: 1161169 (C4 (Web Text))

Max Activating Token Index: 771

Text #6

Max Range: 5.0597. Min Range: -5.0597

Max Act: 3.8850. Min Act: -0.0000

Data Index: 299169 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 5.0597. Min Range: -5.0597

Max Act: 3.6959. Min Act: -0.0000

Data Index: 425117 (C4 (Web Text))

Max Activating Token Index: 1015

Text #8

Max Range: 5.0597. Min Range: -5.0597

Max Act: 3.5653. Min Act: -0.0000

Data Index: 942843 (C4 (Web Text))

Max Activating Token Index: 809

Text #9

Max Range: 5.0597. Min Range: -5.0597

Max Act: 3.7360. Min Act: -0.0000

Data Index: 716275 (C4 (Web Text))

Max Activating Token Index: 874

Text #10

Max Range: 5.0597. Min Range: -5.0597

Max Act: 3.7813. Min Act: -0.0000

Data Index: 280675 (C4 (Web Text))

Max Activating Token Index: 51

Text #11

Max Range: 5.0597. Min Range: -5.0597

Max Act: 3.6311. Min Act: -0.0000

Data Index: 570125 (C4 (Web Text))

Max Activating Token Index: 516

Text #12

Max Range: 5.0597. Min Range: -5.0597

Max Act: 3.5906. Min Act: -0.0000

Data Index: 991293 (C4 (Web Text))

Max Activating Token Index: 621

Text #13

Max Range: 5.0597. Min Range: -5.0597

Max Act: 3.4386. Min Act: -0.0000

Data Index: 1089583 (C4 (Web Text))

Max Activating Token Index: 522

Text #14

Max Range: 5.0597. Min Range: -5.0597

Max Act: 3.3560. Min Act: -0.0000

Data Index: 1337560 (C4 (Web Text))

Max Activating Token Index: 576

Text #15

Max Range: 5.0597. Min Range: -5.0597

Max Act: 3.4813. Min Act: -0.0000

Data Index: 791349 (C4 (Web Text))

Max Activating Token Index: 649

Text #16

Max Range: 5.0597. Min Range: -5.0597

Max Act: 3.2290. Min Act: -0.0000

Data Index: 612689 (C4 (Web Text))

Max Activating Token Index: 83

Text #17

Max Range: 5.0597. Min Range: -5.0597

Max Act: 3.2147. Min Act: -0.0000

Data Index: 722617 (C4 (Web Text))

Max Activating Token Index: 758

Text #18

Max Range: 5.0597. Min Range: -5.0597

Max Act: 3.2484. Min Act: -0.0000

Data Index: 754219 (C4 (Web Text))

Max Activating Token Index: 164

Text #19

Max Range: 5.0597. Min Range: -5.0597

Max Act: 3.1969. Min Act: -0.0000

Data Index: 672067 (C4 (Web Text))

Max Activating Token Index: 956