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

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

Neuron 5174 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: 0.8644. Min Range: -0.8644

Max Act: 0.8644. Min Act: -0.0001

Data Index: 175443 (C4 (Web Text))

Max Activating Token Index: 100

Text #1

Max Range: 0.8644. Min Range: -0.8644

Max Act: 0.8463. Min Act: -0.0001

Data Index: 1194867 (C4 (Web Text))

Max Activating Token Index: 736

Text #2

Max Range: 0.8644. Min Range: -0.8644

Max Act: 0.8434. Min Act: -0.0001

Data Index: 227563 (C4 (Web Text))

Max Activating Token Index: 71

Text #3

Max Range: 0.8644. Min Range: -0.8644

Max Act: 0.8401. Min Act: -0.0001

Data Index: 996097 (C4 (Web Text))

Max Activating Token Index: 754

Text #4

Max Range: 0.8644. Min Range: -0.8644

Max Act: 0.8472. Min Act: -0.0001

Data Index: 639457 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.8644. Min Range: -0.8644

Max Act: 0.8148. Min Act: -0.0001

Data Index: 505053 (C4 (Web Text))

Max Activating Token Index: 859

Text #6

Max Range: 0.8644. Min Range: -0.8644

Max Act: 0.7950. Min Act: -0.0001

Data Index: 220756 (C4 (Web Text))

Max Activating Token Index: 234

Text #7

Max Range: 0.8644. Min Range: -0.8644

Max Act: 0.8088. Min Act: -0.0001

Data Index: 114136 (C4 (Web Text))

Max Activating Token Index: 970

Text #8

Max Range: 0.8644. Min Range: -0.8644

Max Act: 0.8037. Min Act: -0.0001

Data Index: 1056200 (C4 (Web Text))

Max Activating Token Index: 220

Text #9

Max Range: 0.8644. Min Range: -0.8644

Max Act: 0.7839. Min Act: -0.0001

Data Index: 791934 (C4 (Web Text))

Max Activating Token Index: 112

Text #10

Max Range: 0.8644. Min Range: -0.8644

Max Act: 0.8003. Min Act: -0.0001

Data Index: 611546 (C4 (Web Text))

Max Activating Token Index: 717

Text #11

Max Range: 0.8644. Min Range: -0.8644

Max Act: 0.7845. Min Act: -0.0001

Data Index: 398139 (C4 (Web Text))

Max Activating Token Index: 716

Text #12

Max Range: 0.8644. Min Range: -0.8644

Max Act: 0.7892. Min Act: -0.0001

Data Index: 966623 (C4 (Web Text))

Max Activating Token Index: 501

Text #13

Max Range: 0.8644. Min Range: -0.8644

Max Act: 0.7802. Min Act: -0.0001

Data Index: 368288 (C4 (Web Text))

Max Activating Token Index: 43

Text #14

Max Range: 0.8644. Min Range: -0.8644

Max Act: 0.7981. Min Act: -0.0001

Data Index: 1151989 (C4 (Web Text))

Max Activating Token Index: 307

Text #15

Max Range: 0.8644. Min Range: -0.8644

Max Act: 0.7865. Min Act: -0.0001

Data Index: 1208258 (C4 (Web Text))

Max Activating Token Index: 994

Text #16

Max Range: 0.8644. Min Range: -0.8644

Max Act: 0.7858. Min Act: -0.0001

Data Index: 663373 (C4 (Web Text))

Max Activating Token Index: 816

Text #17

Max Range: 0.8644. Min Range: -0.8644

Max Act: 0.7713. Min Act: -0.0001

Data Index: 265727 (C4 (Web Text))

Max Activating Token Index: 359

Text #18

Max Range: 0.8644. Min Range: -0.8644

Max Act: 0.7780. Min Act: -0.0001

Data Index: 316652 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.8644. Min Range: -0.8644

Max Act: 0.7744. Min Act: -0.0001

Data Index: 991494 (C4 (Web Text))

Max Activating Token Index: 460