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

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

Neuron 3595 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: 2.0057. Min Range: -2.0057

Max Act: 2.0057. Min Act: -0.0001

Data Index: 1137300 (C4 (Web Text))

Max Activating Token Index: 56

Text #1

Max Range: 2.0057. Min Range: -2.0057

Max Act: 1.8089. Min Act: -0.0000

Data Index: 888730 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 2.0057. Min Range: -2.0057

Max Act: 1.4819. Min Act: -0.0000

Data Index: 238934 (C4 (Web Text))

Max Activating Token Index: 832

Text #3

Max Range: 2.0057. Min Range: -2.0057

Max Act: 1.7211. Min Act: -0.0000

Data Index: 1359167 (C4 (Web Text))

Max Activating Token Index: 126

Text #4

Max Range: 2.0057. Min Range: -2.0057

Max Act: 1.7198. Min Act: -0.0000

Data Index: 58697 (C4 (Web Text))

Max Activating Token Index: 675

Text #5

Max Range: 2.0057. Min Range: -2.0057

Max Act: 1.5799. Min Act: -0.0000

Data Index: 497067 (C4 (Web Text))

Max Activating Token Index: 774

Text #6

Max Range: 2.0057. Min Range: -2.0057

Max Act: 1.6175. Min Act: -0.0001

Data Index: 742160 (C4 (Web Text))

Max Activating Token Index: 931

Text #7

Max Range: 2.0057. Min Range: -2.0057

Max Act: 1.6141. Min Act: -0.0001

Data Index: 603061 (C4 (Web Text))

Max Activating Token Index: 471

Text #8

Max Range: 2.0057. Min Range: -2.0057

Max Act: 1.5892. Min Act: -0.0000

Data Index: 300431 (C4 (Web Text))

Max Activating Token Index: 1021

Text #9

Max Range: 2.0057. Min Range: -2.0057

Max Act: 1.6277. Min Act: -0.0000

Data Index: 394440 (C4 (Web Text))

Max Activating Token Index: 57

Text #10

Max Range: 2.0057. Min Range: -2.0057

Max Act: 1.5620. Min Act: -0.0001

Data Index: 964795 (C4 (Web Text))

Max Activating Token Index: 42

Text #11

Max Range: 2.0057. Min Range: -2.0057

Max Act: 1.4042. Min Act: -0.0001

Data Index: 1171081 (C4 (Web Text))

Max Activating Token Index: 944

Text #12

Max Range: 2.0057. Min Range: -2.0057

Max Act: 1.5306. Min Act: -0.0001

Data Index: 1305347 (C4 (Web Text))

Max Activating Token Index: 445

Text #13

Max Range: 2.0057. Min Range: -2.0057

Max Act: 1.5587. Min Act: -0.0001

Data Index: 192169 (C4 (Web Text))

Max Activating Token Index: 948

Text #14

Max Range: 2.0057. Min Range: -2.0057

Max Act: 1.5315. Min Act: -0.0000

Data Index: 1190261 (C4 (Web Text))

Max Activating Token Index: 512

Text #15

Max Range: 2.0057. Min Range: -2.0057

Max Act: 1.5262. Min Act: -0.0001

Data Index: 263373 (C4 (Web Text))

Max Activating Token Index: 299

Text #16

Max Range: 2.0057. Min Range: -2.0057

Max Act: 1.6012. Min Act: -0.0000

Data Index: 695530 (C4 (Web Text))

Max Activating Token Index: 412

Text #17

Max Range: 2.0057. Min Range: -2.0057

Max Act: 1.4440. Min Act: -0.0000

Data Index: 923470 (C4 (Web Text))

Max Activating Token Index: 756

Text #18

Max Range: 2.0057. Min Range: -2.0057

Max Act: 1.5021. Min Act: -0.0000

Data Index: 937202 (C4 (Web Text))

Max Activating Token Index: 745

Text #19

Max Range: 2.0057. Min Range: -2.0057

Max Act: 1.4229. Min Act: -0.0001

Data Index: 208997 (C4 (Web Text))

Max Activating Token Index: 617