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

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

Neuron 3474 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: 0.0079. Min Range: -0.0079

Max Act: 0.0079. Min Act: -0.0002

Data Index: 1482739 (Python Code)

Max Activating Token Index: 13

Text #1

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0074. Min Act: -0.0003

Data Index: 662110 (C4 (Web Text))

Max Activating Token Index: 177

Text #2

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0074. Min Act: -0.0002

Data Index: 1450222 (Python Code)

Max Activating Token Index: 3

Text #3

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0071. Min Act: -0.0003

Data Index: 34950 (C4 (Web Text))

Max Activating Token Index: 229

Text #4

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0068. Min Act: -0.0003

Data Index: 476627 (C4 (Web Text))

Max Activating Token Index: 906

Text #5

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0069. Min Act: -0.0003

Data Index: 1081802 (C4 (Web Text))

Max Activating Token Index: 545

Text #6

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0067. Min Act: -0.0003

Data Index: 348804 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0066. Min Act: -0.0003

Data Index: 1076956 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0067. Min Act: -0.0003

Data Index: 824752 (C4 (Web Text))

Max Activating Token Index: 68

Text #9

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0065. Min Act: -0.0003

Data Index: 647313 (C4 (Web Text))

Max Activating Token Index: 631

Text #10

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0063. Min Act: -0.0003

Data Index: 821622 (C4 (Web Text))

Max Activating Token Index: 646

Text #11

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0065. Min Act: -0.0003

Data Index: 468974 (C4 (Web Text))

Max Activating Token Index: 821

Text #12

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0064. Min Act: -0.0003

Data Index: 618485 (C4 (Web Text))

Max Activating Token Index: 596

Text #13

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0064. Min Act: -0.0003

Data Index: 989345 (C4 (Web Text))

Max Activating Token Index: 933

Text #14

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0063. Min Act: -0.0002

Data Index: 1592017 (Python Code)

Max Activating Token Index: 12

Text #15

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0063. Min Act: -0.0003

Data Index: 811249 (C4 (Web Text))

Max Activating Token Index: 171

Text #16

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0063. Min Act: -0.0003

Data Index: 1063166 (C4 (Web Text))

Max Activating Token Index: 292

Text #17

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0064. Min Act: -0.0003

Data Index: 945777 (C4 (Web Text))

Max Activating Token Index: 380

Text #18

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0063. Min Act: -0.0003

Data Index: 1119597 (C4 (Web Text))

Max Activating Token Index: 160

Text #19

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0063. Min Act: -0.0003

Data Index: 105223 (C4 (Web Text))

Max Activating Token Index: 659