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

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

Neuron 4899 in Layer 0

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: 0.1020. Min Range: -0.1020

Max Act: 0.1020. Min Act: -0.0001

Data Index: 641167 (C4 (Web Text))

Max Activating Token Index: 86

Text #1

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0939. Min Act: -0.0001

Data Index: 965959 (C4 (Web Text))

Max Activating Token Index: 95

Text #2

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0889. Min Act: -0.0001

Data Index: 1250737 (C4 (Web Text))

Max Activating Token Index: 650

Text #3

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0892. Min Act: -0.0001

Data Index: 369384 (C4 (Web Text))

Max Activating Token Index: 126

Text #4

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0871. Min Act: -0.0001

Data Index: 57432 (C4 (Web Text))

Max Activating Token Index: 268

Text #5

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0864. Min Act: -0.0001

Data Index: 592976 (C4 (Web Text))

Max Activating Token Index: 541

Text #6

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0882. Min Act: -0.0001

Data Index: 1257568 (C4 (Web Text))

Max Activating Token Index: 11

Text #7

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0866. Min Act: -0.0001

Data Index: 513723 (C4 (Web Text))

Max Activating Token Index: 166

Text #8

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0865. Min Act: -0.0001

Data Index: 1136316 (C4 (Web Text))

Max Activating Token Index: 301

Text #9

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0858. Min Act: -0.0001

Data Index: 820988 (C4 (Web Text))

Max Activating Token Index: 409

Text #10

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0870. Min Act: -0.0001

Data Index: 458536 (C4 (Web Text))

Max Activating Token Index: 677

Text #11

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0855. Min Act: -0.0001

Data Index: 106496 (C4 (Web Text))

Max Activating Token Index: 141

Text #12

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0846. Min Act: -0.0001

Data Index: 991734 (C4 (Web Text))

Max Activating Token Index: 163

Text #13

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0835. Min Act: -0.0001

Data Index: 555511 (C4 (Web Text))

Max Activating Token Index: 143

Text #14

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0844. Min Act: -0.0001

Data Index: 327936 (C4 (Web Text))

Max Activating Token Index: 7

Text #15

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0820. Min Act: -0.0001

Data Index: 777949 (C4 (Web Text))

Max Activating Token Index: 428

Text #16

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0830. Min Act: -0.0001

Data Index: 920159 (C4 (Web Text))

Max Activating Token Index: 1014

Text #17

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0839. Min Act: -0.0001

Data Index: 503554 (C4 (Web Text))

Max Activating Token Index: 62

Text #18

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0819. Min Act: -0.0001

Data Index: 495110 (C4 (Web Text))

Max Activating Token Index: 212

Text #19

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0829. Min Act: -0.0001

Data Index: 1243035 (C4 (Web Text))

Max Activating Token Index: 266