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

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

Neuron 1404 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3654. Min Act: -0.0000

Data Index: 556389 (C4 (Web Text))

Max Activating Token Index: 667

Text #1

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3565. Min Act: -0.0001

Data Index: 312156 (C4 (Web Text))

Max Activating Token Index: 147

Text #2

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3527. Min Act: -0.0000

Data Index: 472770 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3607. Min Act: -0.0001

Data Index: 857751 (C4 (Web Text))

Max Activating Token Index: 123

Text #4

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3451. Min Act: -0.0000

Data Index: 1043712 (C4 (Web Text))

Max Activating Token Index: 29

Text #5

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3365. Min Act: -0.0000

Data Index: 124309 (C4 (Web Text))

Max Activating Token Index: 835

Text #6

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3348. Min Act: -0.0000

Data Index: 1214431 (C4 (Web Text))

Max Activating Token Index: 710

Text #7

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3220. Min Act: -0.0000

Data Index: 957338 (C4 (Web Text))

Max Activating Token Index: 112

Text #8

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3267. Min Act: -0.0000

Data Index: 656507 (C4 (Web Text))

Max Activating Token Index: 181

Text #9

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3244. Min Act: -0.0000

Data Index: 122394 (C4 (Web Text))

Max Activating Token Index: 793

Text #10

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3257. Min Act: -0.0000

Data Index: 871492 (C4 (Web Text))

Max Activating Token Index: 834

Text #11

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3091. Min Act: -0.0001

Data Index: 767766 (C4 (Web Text))

Max Activating Token Index: 89

Text #12

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3092. Min Act: -0.0000

Data Index: 709384 (C4 (Web Text))

Max Activating Token Index: 334

Text #13

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.2925. Min Act: -0.0000

Data Index: 337389 (C4 (Web Text))

Max Activating Token Index: 68

Text #14

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.2934. Min Act: -0.0000

Data Index: 1086742 (C4 (Web Text))

Max Activating Token Index: 418

Text #15

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3013. Min Act: 0.0000

Data Index: 544096 (C4 (Web Text))

Max Activating Token Index: 98

Text #16

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.2978. Min Act: -0.0000

Data Index: 751707 (C4 (Web Text))

Max Activating Token Index: 294

Text #17

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3085. Min Act: -0.0000

Data Index: 1208295 (C4 (Web Text))

Max Activating Token Index: 395

Text #18

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.2971. Min Act: -0.0000

Data Index: 735456 (C4 (Web Text))

Max Activating Token Index: 862

Text #19

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.2980. Min Act: -0.0000

Data Index: 741101 (C4 (Web Text))

Max Activating Token Index: 232