Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3347 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1223. Min Act: -0.0002

Data Index: 53208 (C4 (Web Text))

Max Activating Token Index: 705

Text #1

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1146. Min Act: -0.0003

Data Index: 430716 (C4 (Web Text))

Max Activating Token Index: 990

Text #2

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1080. Min Act: -0.0002

Data Index: 890713 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1048. Min Act: -0.0002

Data Index: 368474 (C4 (Web Text))

Max Activating Token Index: 917

Text #4

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1012. Min Act: -0.0002

Data Index: 778800 (C4 (Web Text))

Max Activating Token Index: 284

Text #5

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1001. Min Act: -0.0002

Data Index: 756224 (C4 (Web Text))

Max Activating Token Index: 93

Text #6

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0979. Min Act: -0.0002

Data Index: 164971 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0992. Min Act: -0.0002

Data Index: 327493 (C4 (Web Text))

Max Activating Token Index: 150

Text #8

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0969. Min Act: -0.0002

Data Index: 167099 (C4 (Web Text))

Max Activating Token Index: 94

Text #9

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0921. Min Act: -0.0002

Data Index: 224355 (C4 (Web Text))

Max Activating Token Index: 84

Text #10

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0903. Min Act: -0.0002

Data Index: 260934 (C4 (Web Text))

Max Activating Token Index: 711

Text #11

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0876. Min Act: -0.0002

Data Index: 832822 (C4 (Web Text))

Max Activating Token Index: 138

Text #12

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0893. Min Act: -0.0002

Data Index: 470482 (C4 (Web Text))

Max Activating Token Index: 818

Text #13

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0885. Min Act: -0.0002

Data Index: 966873 (C4 (Web Text))

Max Activating Token Index: 671

Text #14

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0891. Min Act: -0.0003

Data Index: 1222329 (C4 (Web Text))

Max Activating Token Index: 131

Text #15

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0891. Min Act: -0.0003

Data Index: 335913 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0880. Min Act: -0.0002

Data Index: 650052 (C4 (Web Text))

Max Activating Token Index: 40

Text #17

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0865. Min Act: -0.0002

Data Index: 665877 (C4 (Web Text))

Max Activating Token Index: 307

Text #18

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0858. Min Act: -0.0002

Data Index: 524113 (C4 (Web Text))

Max Activating Token Index: 126

Text #19

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0864. Min Act: -0.0002

Data Index: 881504 (C4 (Web Text))

Max Activating Token Index: 106