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

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

Neuron 2944 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: 0.0066. Min Range: -0.0066

Max Act: 0.0066. Min Act: -0.0003

Data Index: 489238 (C4 (Web Text))

Max Activating Token Index: 141

Text #1

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0066. Min Act: -0.0003

Data Index: 619301 (C4 (Web Text))

Max Activating Token Index: 215

Text #2

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0066. Min Act: -0.0003

Data Index: 280467 (C4 (Web Text))

Max Activating Token Index: 163

Text #3

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0066. Min Act: -0.0003

Data Index: 498721 (C4 (Web Text))

Max Activating Token Index: 123

Text #4

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0065. Min Act: -0.0003

Data Index: 891920 (C4 (Web Text))

Max Activating Token Index: 150

Text #5

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0064. Min Act: -0.0003

Data Index: 365145 (C4 (Web Text))

Max Activating Token Index: 785

Text #6

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0064. Min Act: -0.0003

Data Index: 89104 (C4 (Web Text))

Max Activating Token Index: 108

Text #7

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0064. Min Act: -0.0003

Data Index: 281945 (C4 (Web Text))

Max Activating Token Index: 729

Text #8

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0064. Min Act: -0.0003

Data Index: 387607 (C4 (Web Text))

Max Activating Token Index: 759

Text #9

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0064. Min Act: -0.0003

Data Index: 1038164 (C4 (Web Text))

Max Activating Token Index: 112

Text #10

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0064. Min Act: -0.0003

Data Index: 1250407 (C4 (Web Text))

Max Activating Token Index: 419

Text #11

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0064. Min Act: -0.0003

Data Index: 401810 (C4 (Web Text))

Max Activating Token Index: 476

Text #12

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0063. Min Act: -0.0003

Data Index: 928862 (C4 (Web Text))

Max Activating Token Index: 145

Text #13

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0063. Min Act: -0.0003

Data Index: 639680 (C4 (Web Text))

Max Activating Token Index: 119

Text #14

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0063. Min Act: -0.0003

Data Index: 449328 (C4 (Web Text))

Max Activating Token Index: 831

Text #15

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0063. Min Act: -0.0003

Data Index: 24193 (C4 (Web Text))

Max Activating Token Index: 495

Text #16

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0063. Min Act: -0.0003

Data Index: 856302 (C4 (Web Text))

Max Activating Token Index: 445

Text #17

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0063. Min Act: -0.0003

Data Index: 218532 (C4 (Web Text))

Max Activating Token Index: 98

Text #18

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0063. Min Act: -0.0003

Data Index: 380941 (C4 (Web Text))

Max Activating Token Index: 250

Text #19

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0063. Min Act: -0.0003

Data Index: 24835 (C4 (Web Text))

Max Activating Token Index: 563