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

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

Neuron 4051 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1347. Min Act: -0.0001

Data Index: 973177 (C4 (Web Text))

Max Activating Token Index: 457

Text #1

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1115. Min Act: -0.0001

Data Index: 978924 (C4 (Web Text))

Max Activating Token Index: 694

Text #2

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1133. Min Act: -0.0001

Data Index: 771515 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1047. Min Act: -0.0001

Data Index: 152634 (C4 (Web Text))

Max Activating Token Index: 477

Text #4

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1023. Min Act: -0.0001

Data Index: 707097 (C4 (Web Text))

Max Activating Token Index: 318

Text #5

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1015. Min Act: -0.0001

Data Index: 13009 (C4 (Web Text))

Max Activating Token Index: 472

Text #6

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1039. Min Act: -0.0001

Data Index: 538478 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.0995. Min Act: -0.0001

Data Index: 907007 (C4 (Web Text))

Max Activating Token Index: 227

Text #8

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.0955. Min Act: -0.0001

Data Index: 742655 (C4 (Web Text))

Max Activating Token Index: 132

Text #9

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.0991. Min Act: -0.0001

Data Index: 171675 (C4 (Web Text))

Max Activating Token Index: 611

Text #10

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.0991. Min Act: -0.0001

Data Index: 708253 (C4 (Web Text))

Max Activating Token Index: 54

Text #11

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.0968. Min Act: -0.0001

Data Index: 886027 (C4 (Web Text))

Max Activating Token Index: 994

Text #12

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.0942. Min Act: -0.0001

Data Index: 636368 (C4 (Web Text))

Max Activating Token Index: 119

Text #13

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.0976. Min Act: -0.0001

Data Index: 98950 (C4 (Web Text))

Max Activating Token Index: 165

Text #14

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.0924. Min Act: -0.0001

Data Index: 1088475 (C4 (Web Text))

Max Activating Token Index: 783

Text #15

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.0888. Min Act: -0.0001

Data Index: 762116 (C4 (Web Text))

Max Activating Token Index: 151

Text #16

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.0939. Min Act: -0.0001

Data Index: 1300598 (C4 (Web Text))

Max Activating Token Index: 51

Text #17

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.0955. Min Act: -0.0001

Data Index: 241431 (C4 (Web Text))

Max Activating Token Index: 953

Text #18

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.0958. Min Act: -0.0001

Data Index: 410711 (C4 (Web Text))

Max Activating Token Index: 996

Text #19

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.0884. Min Act: -0.0001

Data Index: 420908 (C4 (Web Text))

Max Activating Token Index: 879