Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4651 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0053. Min Act: -0.0002

Data Index: 764520 (C4 (Web Text))

Max Activating Token Index: 414

Text #1

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0053. Min Act: -0.0002

Data Index: 1049976 (C4 (Web Text))

Max Activating Token Index: 314

Text #2

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0051. Min Act: -0.0002

Data Index: 935666 (C4 (Web Text))

Max Activating Token Index: 126

Text #3

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0050. Min Act: -0.0002

Data Index: 933995 (C4 (Web Text))

Max Activating Token Index: 58

Text #4

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0049. Min Act: -0.0002

Data Index: 495040 (C4 (Web Text))

Max Activating Token Index: 73

Text #5

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0048. Min Act: -0.0002

Data Index: 192988 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0049. Min Act: -0.0002

Data Index: 473637 (C4 (Web Text))

Max Activating Token Index: 100

Text #7

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0050. Min Act: -0.0002

Data Index: 170060 (C4 (Web Text))

Max Activating Token Index: 208

Text #8

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0049. Min Act: -0.0002

Data Index: 337690 (C4 (Web Text))

Max Activating Token Index: 21

Text #9

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0047. Min Act: -0.0002

Data Index: 22145 (C4 (Web Text))

Max Activating Token Index: 51

Text #10

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0048. Min Act: -0.0002

Data Index: 559184 (C4 (Web Text))

Max Activating Token Index: 27

Text #11

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0048. Min Act: -0.0002

Data Index: 585692 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0048. Min Act: -0.0002

Data Index: 468317 (C4 (Web Text))

Max Activating Token Index: 157

Text #13

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0048. Min Act: -0.0002

Data Index: 587557 (C4 (Web Text))

Max Activating Token Index: 141

Text #14

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0048. Min Act: -0.0002

Data Index: 456880 (C4 (Web Text))

Max Activating Token Index: 40

Text #15

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0048. Min Act: -0.0002

Data Index: 391314 (C4 (Web Text))

Max Activating Token Index: 661

Text #16

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0047. Min Act: -0.0002

Data Index: 1022369 (C4 (Web Text))

Max Activating Token Index: 342

Text #17

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0048. Min Act: -0.0002

Data Index: 1004568 (C4 (Web Text))

Max Activating Token Index: 64

Text #18

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0047. Min Act: -0.0002

Data Index: 347437 (C4 (Web Text))

Max Activating Token Index: 52

Text #19

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0047. Min Act: -0.0002

Data Index: 671043 (C4 (Web Text))

Max Activating Token Index: 446