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

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

Neuron 65 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0050. Min Act: -0.0003

Data Index: 1275919 (C4 (Web Text))

Max Activating Token Index: 105

Text #1

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0050. Min Act: -0.0003

Data Index: 909631 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0048. Min Act: -0.0003

Data Index: 1040547 (C4 (Web Text))

Max Activating Token Index: 93

Text #3

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0048. Min Act: -0.0003

Data Index: 132926 (C4 (Web Text))

Max Activating Token Index: 179

Text #4

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0048. Min Act: -0.0003

Data Index: 806790 (C4 (Web Text))

Max Activating Token Index: 339

Text #5

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0048. Min Act: -0.0002

Data Index: 44347 (C4 (Web Text))

Max Activating Token Index: 968

Text #6

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0048. Min Act: -0.0003

Data Index: 307213 (C4 (Web Text))

Max Activating Token Index: 581

Text #7

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0047. Min Act: -0.0003

Data Index: 1322701 (C4 (Web Text))

Max Activating Token Index: 69

Text #8

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0047. Min Act: -0.0003

Data Index: 1003363 (C4 (Web Text))

Max Activating Token Index: 143

Text #9

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0047. Min Act: -0.0003

Data Index: 897463 (C4 (Web Text))

Max Activating Token Index: 66

Text #10

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0046. Min Act: -0.0003

Data Index: 881512 (C4 (Web Text))

Max Activating Token Index: 550

Text #11

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0047. Min Act: -0.0003

Data Index: 266024 (C4 (Web Text))

Max Activating Token Index: 112

Text #12

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0045. Min Act: -0.0003

Data Index: 54371 (C4 (Web Text))

Max Activating Token Index: 628

Text #13

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0046. Min Act: -0.0003

Data Index: 580400 (C4 (Web Text))

Max Activating Token Index: 88

Text #14

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0046. Min Act: -0.0003

Data Index: 1261045 (C4 (Web Text))

Max Activating Token Index: 65

Text #15

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0046. Min Act: -0.0003

Data Index: 381493 (C4 (Web Text))

Max Activating Token Index: 250

Text #16

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0045. Min Act: -0.0003

Data Index: 858157 (C4 (Web Text))

Max Activating Token Index: 303

Text #17

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0045. Min Act: -0.0003

Data Index: 743817 (C4 (Web Text))

Max Activating Token Index: 40

Text #18

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0045. Min Act: -0.0003

Data Index: 114594 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0045. Min Act: -0.0003

Data Index: 287612 (C4 (Web Text))

Max Activating Token Index: 19