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

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

Neuron 5787 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: 0.9225. Min Range: -0.9225

Max Act: 0.9225. Min Act: -0.0001

Data Index: 124608 (C4 (Web Text))

Max Activating Token Index: 993

Text #1

Max Range: 0.9225. Min Range: -0.9225

Max Act: 0.6267. Min Act: -0.0000

Data Index: 200218 (C4 (Web Text))

Max Activating Token Index: 956

Text #2

Max Range: 0.9225. Min Range: -0.9225

Max Act: 0.6885. Min Act: -0.0000

Data Index: 332586 (C4 (Web Text))

Max Activating Token Index: 995

Text #3

Max Range: 0.9225. Min Range: -0.9225

Max Act: 0.5569. Min Act: -0.0000

Data Index: 64781 (C4 (Web Text))

Max Activating Token Index: 532

Text #4

Max Range: 0.9225. Min Range: -0.9225

Max Act: 0.5791. Min Act: -0.0000

Data Index: 1265517 (C4 (Web Text))

Max Activating Token Index: 981

Text #5

Max Range: 0.9225. Min Range: -0.9225

Max Act: 0.4978. Min Act: -0.0000

Data Index: 1010675 (C4 (Web Text))

Max Activating Token Index: 457

Text #6

Max Range: 0.9225. Min Range: -0.9225

Max Act: 0.5323. Min Act: -0.0000

Data Index: 1060674 (C4 (Web Text))

Max Activating Token Index: 713

Text #7

Max Range: 0.9225. Min Range: -0.9225

Max Act: 0.5261. Min Act: -0.0000

Data Index: 356253 (C4 (Web Text))

Max Activating Token Index: 15

Text #8

Max Range: 0.9225. Min Range: -0.9225

Max Act: 0.4929. Min Act: -0.0000

Data Index: 654231 (C4 (Web Text))

Max Activating Token Index: 1005

Text #9

Max Range: 0.9225. Min Range: -0.9225

Max Act: 0.4952. Min Act: -0.0000

Data Index: 903955 (C4 (Web Text))

Max Activating Token Index: 415

Text #10

Max Range: 0.9225. Min Range: -0.9225

Max Act: 0.4621. Min Act: -0.0000

Data Index: 42236 (C4 (Web Text))

Max Activating Token Index: 936

Text #11

Max Range: 0.9225. Min Range: -0.9225

Max Act: 0.4568. Min Act: -0.0000

Data Index: 1007285 (C4 (Web Text))

Max Activating Token Index: 549

Text #12

Max Range: 0.9225. Min Range: -0.9225

Max Act: 0.4507. Min Act: -0.0000

Data Index: 553466 (C4 (Web Text))

Max Activating Token Index: 682

Text #13

Max Range: 0.9225. Min Range: -0.9225

Max Act: 0.4557. Min Act: -0.0000

Data Index: 854098 (C4 (Web Text))

Max Activating Token Index: 924

Text #14

Max Range: 0.9225. Min Range: -0.9225

Max Act: 0.4414. Min Act: -0.0000

Data Index: 1071993 (C4 (Web Text))

Max Activating Token Index: 925

Text #15

Max Range: 0.9225. Min Range: -0.9225

Max Act: 0.4411. Min Act: -0.0000

Data Index: 743724 (C4 (Web Text))

Max Activating Token Index: 922

Text #16

Max Range: 0.9225. Min Range: -0.9225

Max Act: 0.4303. Min Act: -0.0000

Data Index: 411577 (C4 (Web Text))

Max Activating Token Index: 214

Text #17

Max Range: 0.9225. Min Range: -0.9225

Max Act: 0.2942. Min Act: -0.0000

Data Index: 1305915 (C4 (Web Text))

Max Activating Token Index: 192

Text #18

Max Range: 0.9225. Min Range: -0.9225

Max Act: 0.4354. Min Act: -0.0000

Data Index: 125589 (C4 (Web Text))

Max Activating Token Index: 738

Text #19

Max Range: 0.9225. Min Range: -0.9225

Max Act: 0.4301. Min Act: -0.0000

Data Index: 1223191 (C4 (Web Text))

Max Activating Token Index: 789