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

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

Neuron 2888 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3984. Min Range: -0.3984

Max Act: 0.3984. Min Act: -0.0000

Data Index: 1157270 (C4 (Web Text))

Max Activating Token Index: 1006

Text #1

Max Range: 0.3984. Min Range: -0.3984

Max Act: 0.3056. Min Act: -0.0000

Data Index: 461120 (C4 (Web Text))

Max Activating Token Index: 739

Text #2

Max Range: 0.3984. Min Range: -0.3984

Max Act: 0.2944. Min Act: -0.0001

Data Index: 772519 (C4 (Web Text))

Max Activating Token Index: 136

Text #3

Max Range: 0.3984. Min Range: -0.3984

Max Act: 0.3021. Min Act: -0.0001

Data Index: 1340139 (C4 (Web Text))

Max Activating Token Index: 75

Text #4

Max Range: 0.3984. Min Range: -0.3984

Max Act: 0.2906. Min Act: -0.0001

Data Index: 539605 (C4 (Web Text))

Max Activating Token Index: 122

Text #5

Max Range: 0.3984. Min Range: -0.3984

Max Act: 0.3054. Min Act: -0.0001

Data Index: 1074065 (C4 (Web Text))

Max Activating Token Index: 465

Text #6

Max Range: 0.3984. Min Range: -0.3984

Max Act: 0.2828. Min Act: -0.0001

Data Index: 1171974 (C4 (Web Text))

Max Activating Token Index: 100

Text #7

Max Range: 0.3984. Min Range: -0.3984

Max Act: 0.2597. Min Act: -0.0001

Data Index: 70419 (C4 (Web Text))

Max Activating Token Index: 868

Text #8

Max Range: 0.3984. Min Range: -0.3984

Max Act: 0.2697. Min Act: -0.0000

Data Index: 349878 (C4 (Web Text))

Max Activating Token Index: 826

Text #9

Max Range: 0.3984. Min Range: -0.3984

Max Act: 0.2651. Min Act: -0.0000

Data Index: 81115 (C4 (Web Text))

Max Activating Token Index: 678

Text #10

Max Range: 0.3984. Min Range: -0.3984

Max Act: 0.2761. Min Act: -0.0001

Data Index: 385859 (C4 (Web Text))

Max Activating Token Index: 230

Text #11

Max Range: 0.3984. Min Range: -0.3984

Max Act: 0.2558. Min Act: -0.0000

Data Index: 1119857 (C4 (Web Text))

Max Activating Token Index: 34

Text #12

Max Range: 0.3984. Min Range: -0.3984

Max Act: 0.2543. Min Act: -0.0001

Data Index: 1073266 (C4 (Web Text))

Max Activating Token Index: 865

Text #13

Max Range: 0.3984. Min Range: -0.3984

Max Act: 0.2585. Min Act: -0.0000

Data Index: 1074429 (C4 (Web Text))

Max Activating Token Index: 706

Text #14

Max Range: 0.3984. Min Range: -0.3984

Max Act: 0.2654. Min Act: -0.0000

Data Index: 604037 (C4 (Web Text))

Max Activating Token Index: 136

Text #15

Max Range: 0.3984. Min Range: -0.3984

Max Act: 0.2678. Min Act: -0.0001

Data Index: 257335 (C4 (Web Text))

Max Activating Token Index: 539

Text #16

Max Range: 0.3984. Min Range: -0.3984

Max Act: 0.2486. Min Act: -0.0001

Data Index: 645769 (C4 (Web Text))

Max Activating Token Index: 138

Text #17

Max Range: 0.3984. Min Range: -0.3984

Max Act: 0.2566. Min Act: -0.0001

Data Index: 1275643 (C4 (Web Text))

Max Activating Token Index: 192

Text #18

Max Range: 0.3984. Min Range: -0.3984

Max Act: 0.2453. Min Act: -0.0000

Data Index: 338 (C4 (Web Text))

Max Activating Token Index: 904

Text #19

Max Range: 0.3984. Min Range: -0.3984

Max Act: 0.2326. Min Act: -0.0001

Data Index: 76081 (C4 (Web Text))

Max Activating Token Index: 834