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

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

Neuron 4971 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.3768. Min Act: -0.0000

Data Index: 493873 (C4 (Web Text))

Max Activating Token Index: 263

Text #1

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.3477. Min Act: -0.0000

Data Index: 1112212 (C4 (Web Text))

Max Activating Token Index: 126

Text #2

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.3189. Min Act: -0.0001

Data Index: 592347 (C4 (Web Text))

Max Activating Token Index: 77

Text #3

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.3592. Min Act: -0.0001

Data Index: 1300628 (C4 (Web Text))

Max Activating Token Index: 916

Text #4

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.3261. Min Act: -0.0001

Data Index: 1329974 (C4 (Web Text))

Max Activating Token Index: 76

Text #5

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.3214. Min Act: -0.0001

Data Index: 749062 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.3109. Min Act: -0.0001

Data Index: 1321029 (C4 (Web Text))

Max Activating Token Index: 457

Text #7

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.3043. Min Act: -0.0001

Data Index: 786300 (C4 (Web Text))

Max Activating Token Index: 48

Text #8

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.2845. Min Act: -0.0000

Data Index: 665403 (C4 (Web Text))

Max Activating Token Index: 142

Text #9

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.3014. Min Act: -0.0000

Data Index: 1015630 (C4 (Web Text))

Max Activating Token Index: 82

Text #10

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.3025. Min Act: -0.0000

Data Index: 1103786 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.3156. Min Act: -0.0001

Data Index: 676662 (C4 (Web Text))

Max Activating Token Index: 183

Text #12

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.2762. Min Act: -0.0001

Data Index: 571077 (C4 (Web Text))

Max Activating Token Index: 289

Text #13

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.2914. Min Act: -0.0000

Data Index: 1210591 (C4 (Web Text))

Max Activating Token Index: 421

Text #14

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.2655. Min Act: -0.0000

Data Index: 1010717 (C4 (Web Text))

Max Activating Token Index: 194

Text #15

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.2776. Min Act: -0.0001

Data Index: 208268 (C4 (Web Text))

Max Activating Token Index: 173

Text #16

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.2925. Min Act: -0.0001

Data Index: 734201 (C4 (Web Text))

Max Activating Token Index: 60

Text #17

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.2732. Min Act: -0.0000

Data Index: 1170863 (C4 (Web Text))

Max Activating Token Index: 580

Text #18

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.2912. Min Act: -0.0000

Data Index: 1072482 (C4 (Web Text))

Max Activating Token Index: 66

Text #19

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.2817. Min Act: -0.0000

Data Index: 1084175 (C4 (Web Text))

Max Activating Token Index: 75