Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2479 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0999. Min Range: -1.0999

Max Act: 1.0685. Min Act: -0.0001

Data Index: 925022 (C4 (Web Text))

Max Activating Token Index: 101

Text #1

Max Range: 1.0999. Min Range: -1.0999

Max Act: 1.0141. Min Act: -0.0001

Data Index: 517515 (C4 (Web Text))

Max Activating Token Index: 848

Text #2

Max Range: 1.0999. Min Range: -1.0999

Max Act: 1.0999. Min Act: -0.0001

Data Index: 30683 (C4 (Web Text))

Max Activating Token Index: 827

Text #3

Max Range: 1.0999. Min Range: -1.0999

Max Act: 0.9711. Min Act: -0.0001

Data Index: 150643 (C4 (Web Text))

Max Activating Token Index: 584

Text #4

Max Range: 1.0999. Min Range: -1.0999

Max Act: 0.7867. Min Act: -0.0001

Data Index: 656354 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 1.0999. Min Range: -1.0999

Max Act: 0.9495. Min Act: -0.0001

Data Index: 610194 (C4 (Web Text))

Max Activating Token Index: 528

Text #6

Max Range: 1.0999. Min Range: -1.0999

Max Act: 0.8480. Min Act: -0.0001

Data Index: 379957 (C4 (Web Text))

Max Activating Token Index: 597

Text #7

Max Range: 1.0999. Min Range: -1.0999

Max Act: 0.8347. Min Act: -0.0001

Data Index: 797586 (C4 (Web Text))

Max Activating Token Index: 214

Text #8

Max Range: 1.0999. Min Range: -1.0999

Max Act: 0.8315. Min Act: -0.0001

Data Index: 1254172 (C4 (Web Text))

Max Activating Token Index: 882

Text #9

Max Range: 1.0999. Min Range: -1.0999

Max Act: 0.7212. Min Act: -0.0001

Data Index: 963066 (C4 (Web Text))

Max Activating Token Index: 890

Text #10

Max Range: 1.0999. Min Range: -1.0999

Max Act: 0.8201. Min Act: -0.0001

Data Index: 884163 (C4 (Web Text))

Max Activating Token Index: 104

Text #11

Max Range: 1.0999. Min Range: -1.0999

Max Act: 0.7208. Min Act: -0.0001

Data Index: 1197806 (C4 (Web Text))

Max Activating Token Index: 768

Text #12

Max Range: 1.0999. Min Range: -1.0999

Max Act: 0.7288. Min Act: -0.0001

Data Index: 1259260 (C4 (Web Text))

Max Activating Token Index: 994

Text #13

Max Range: 1.0999. Min Range: -1.0999

Max Act: 0.6632. Min Act: -0.0001

Data Index: 173583 (C4 (Web Text))

Max Activating Token Index: 424

Text #14

Max Range: 1.0999. Min Range: -1.0999

Max Act: 0.6536. Min Act: -0.0001

Data Index: 489142 (C4 (Web Text))

Max Activating Token Index: 307

Text #15

Max Range: 1.0999. Min Range: -1.0999

Max Act: 0.6556. Min Act: -0.0001

Data Index: 214395 (C4 (Web Text))

Max Activating Token Index: 89

Text #16

Max Range: 1.0999. Min Range: -1.0999

Max Act: 0.6560. Min Act: -0.0001

Data Index: 485287 (C4 (Web Text))

Max Activating Token Index: 454

Text #17

Max Range: 1.0999. Min Range: -1.0999

Max Act: 0.6344. Min Act: -0.0001

Data Index: 1124035 (C4 (Web Text))

Max Activating Token Index: 120

Text #18

Max Range: 1.0999. Min Range: -1.0999

Max Act: 0.6413. Min Act: -0.0001

Data Index: 84170 (C4 (Web Text))

Max Activating Token Index: 634

Text #19

Max Range: 1.0999. Min Range: -1.0999

Max Act: 0.6372. Min Act: -0.0001

Data Index: 425462 (C4 (Web Text))

Max Activating Token Index: 285