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

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

Neuron 3811 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: 1.4014. Min Range: -1.4014

Max Act: 1.4014. Min Act: -0.0002

Data Index: 205189 (C4 (Web Text))

Max Activating Token Index: 2

Text #1

Max Range: 1.4014. Min Range: -1.4014

Max Act: 1.3632. Min Act: -0.0002

Data Index: 514157 (C4 (Web Text))

Max Activating Token Index: 886

Text #2

Max Range: 1.4014. Min Range: -1.4014

Max Act: 1.3322. Min Act: -0.0002

Data Index: 1123902 (C4 (Web Text))

Max Activating Token Index: 353

Text #3

Max Range: 1.4014. Min Range: -1.4014

Max Act: 1.3156. Min Act: -0.0002

Data Index: 96369 (C4 (Web Text))

Max Activating Token Index: 540

Text #4

Max Range: 1.4014. Min Range: -1.4014

Max Act: 1.3216. Min Act: -0.0002

Data Index: 1194063 (C4 (Web Text))

Max Activating Token Index: 724

Text #5

Max Range: 1.4014. Min Range: -1.4014

Max Act: 1.2987. Min Act: -0.0002

Data Index: 650773 (C4 (Web Text))

Max Activating Token Index: 628

Text #6

Max Range: 1.4014. Min Range: -1.4014

Max Act: 1.2874. Min Act: -0.0002

Data Index: 133948 (C4 (Web Text))

Max Activating Token Index: 244

Text #7

Max Range: 1.4014. Min Range: -1.4014

Max Act: 1.3480. Min Act: -0.0002

Data Index: 231180 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 1.4014. Min Range: -1.4014

Max Act: 1.2882. Min Act: -0.0002

Data Index: 330392 (C4 (Web Text))

Max Activating Token Index: 132

Text #9

Max Range: 1.4014. Min Range: -1.4014

Max Act: 1.2929. Min Act: -0.0002

Data Index: 1000569 (C4 (Web Text))

Max Activating Token Index: 495

Text #10

Max Range: 1.4014. Min Range: -1.4014

Max Act: 1.2971. Min Act: -0.0002

Data Index: 1473412 (Python Code)

Max Activating Token Index: 2

Text #11

Max Range: 1.4014. Min Range: -1.4014

Max Act: 1.2971. Min Act: -0.0002

Data Index: 1585748 (Python Code)

Max Activating Token Index: 2

Text #12

Max Range: 1.4014. Min Range: -1.4014

Max Act: 1.2788. Min Act: -0.0002

Data Index: 378571 (C4 (Web Text))

Max Activating Token Index: 792

Text #13

Max Range: 1.4014. Min Range: -1.4014

Max Act: 1.3100. Min Act: -0.0002

Data Index: 793216 (C4 (Web Text))

Max Activating Token Index: 80

Text #14

Max Range: 1.4014. Min Range: -1.4014

Max Act: 1.2840. Min Act: -0.0002

Data Index: 1169450 (C4 (Web Text))

Max Activating Token Index: 898

Text #15

Max Range: 1.4014. Min Range: -1.4014

Max Act: 1.2464. Min Act: -0.0002

Data Index: 1114149 (C4 (Web Text))

Max Activating Token Index: 829

Text #16

Max Range: 1.4014. Min Range: -1.4014

Max Act: 1.2503. Min Act: -0.0002

Data Index: 1111154 (C4 (Web Text))

Max Activating Token Index: 475

Text #17

Max Range: 1.4014. Min Range: -1.4014

Max Act: 1.2509. Min Act: -0.0002

Data Index: 1167913 (C4 (Web Text))

Max Activating Token Index: 771

Text #18

Max Range: 1.4014. Min Range: -1.4014

Max Act: 1.2571. Min Act: -0.0002

Data Index: 1308995 (C4 (Web Text))

Max Activating Token Index: 297

Text #19

Max Range: 1.4014. Min Range: -1.4014

Max Act: 1.2419. Min Act: -0.0002

Data Index: 384261 (C4 (Web Text))

Max Activating Token Index: 301