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

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

Neuron 2976 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9150. Min Range: -3.9150

Max Act: 3.9150. Min Act: -0.0000

Data Index: 217211 (C4 (Web Text))

Max Activating Token Index: 613

Text #1

Max Range: 3.9150. Min Range: -3.9150

Max Act: 3.4352. Min Act: -0.0001

Data Index: 1058652 (C4 (Web Text))

Max Activating Token Index: 932

Text #2

Max Range: 3.9150. Min Range: -3.9150

Max Act: 3.3102. Min Act: -0.0000

Data Index: 558450 (C4 (Web Text))

Max Activating Token Index: 942

Text #3

Max Range: 3.9150. Min Range: -3.9150

Max Act: 3.1290. Min Act: -0.0000

Data Index: 1235061 (C4 (Web Text))

Max Activating Token Index: 1001

Text #4

Max Range: 3.9150. Min Range: -3.9150

Max Act: 2.8632. Min Act: -0.0000

Data Index: 886245 (C4 (Web Text))

Max Activating Token Index: 853

Text #5

Max Range: 3.9150. Min Range: -3.9150

Max Act: 2.8966. Min Act: -0.0000

Data Index: 946061 (C4 (Web Text))

Max Activating Token Index: 687

Text #6

Max Range: 3.9150. Min Range: -3.9150

Max Act: 2.8779. Min Act: -0.0000

Data Index: 1299004 (C4 (Web Text))

Max Activating Token Index: 53

Text #7

Max Range: 3.9150. Min Range: -3.9150

Max Act: 2.5615. Min Act: -0.0000

Data Index: 340574 (C4 (Web Text))

Max Activating Token Index: 910

Text #8

Max Range: 3.9150. Min Range: -3.9150

Max Act: 2.9337. Min Act: -0.0000

Data Index: 294493 (C4 (Web Text))

Max Activating Token Index: 760

Text #9

Max Range: 3.9150. Min Range: -3.9150

Max Act: 2.3569. Min Act: -0.0000

Data Index: 1218715 (C4 (Web Text))

Max Activating Token Index: 968

Text #10

Max Range: 3.9150. Min Range: -3.9150

Max Act: 2.4854. Min Act: -0.0000

Data Index: 73996 (C4 (Web Text))

Max Activating Token Index: 387

Text #11

Max Range: 3.9150. Min Range: -3.9150

Max Act: 2.5115. Min Act: -0.0000

Data Index: 1289048 (C4 (Web Text))

Max Activating Token Index: 160

Text #12

Max Range: 3.9150. Min Range: -3.9150

Max Act: 2.6111. Min Act: -0.0000

Data Index: 1284436 (C4 (Web Text))

Max Activating Token Index: 147

Text #13

Max Range: 3.9150. Min Range: -3.9150

Max Act: 2.5990. Min Act: -0.0000

Data Index: 561434 (C4 (Web Text))

Max Activating Token Index: 658

Text #14

Max Range: 3.9150. Min Range: -3.9150

Max Act: 2.4411. Min Act: -0.0000

Data Index: 340697 (C4 (Web Text))

Max Activating Token Index: 502

Text #15

Max Range: 3.9150. Min Range: -3.9150

Max Act: 2.3011. Min Act: -0.0000

Data Index: 526570 (C4 (Web Text))

Max Activating Token Index: 200

Text #16

Max Range: 3.9150. Min Range: -3.9150

Max Act: 2.3965. Min Act: -0.0000

Data Index: 360572 (C4 (Web Text))

Max Activating Token Index: 831

Text #17

Max Range: 3.9150. Min Range: -3.9150

Max Act: 2.0875. Min Act: -0.0000

Data Index: 751219 (C4 (Web Text))

Max Activating Token Index: 1000

Text #18

Max Range: 3.9150. Min Range: -3.9150

Max Act: 2.5729. Min Act: -0.0000

Data Index: 1007777 (C4 (Web Text))

Max Activating Token Index: 796

Text #19

Max Range: 3.9150. Min Range: -3.9150

Max Act: 2.3113. Min Act: -0.0000

Data Index: 544760 (C4 (Web Text))

Max Activating Token Index: 604