Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 7 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.3144. Min Act: -0.0001

Data Index: 674814 (C4 (Web Text))

Max Activating Token Index: 860

Text #1

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.3569. Min Act: -0.0001

Data Index: 720735 (C4 (Web Text))

Max Activating Token Index: 740

Text #2

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.3411. Min Act: -0.0001

Data Index: 202532 (C4 (Web Text))

Max Activating Token Index: 157

Text #3

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.3387. Min Act: -0.0001

Data Index: 1354809 (C4 (Web Text))

Max Activating Token Index: 957

Text #4

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.3471. Min Act: -0.0001

Data Index: 1233232 (C4 (Web Text))

Max Activating Token Index: 68

Text #5

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.3228. Min Act: -0.0001

Data Index: 23554 (C4 (Web Text))

Max Activating Token Index: 58

Text #6

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.3435. Min Act: -0.0001

Data Index: 1089800 (C4 (Web Text))

Max Activating Token Index: 49

Text #7

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.3319. Min Act: -0.0001

Data Index: 1202727 (C4 (Web Text))

Max Activating Token Index: 528

Text #8

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.3378. Min Act: -0.0001

Data Index: 924194 (C4 (Web Text))

Max Activating Token Index: 624

Text #9

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.3127. Min Act: -0.0001

Data Index: 665722 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.3333. Min Act: -0.0001

Data Index: 1128160 (C4 (Web Text))

Max Activating Token Index: 584

Text #11

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.3073. Min Act: -0.0001

Data Index: 1281690 (C4 (Web Text))

Max Activating Token Index: 216

Text #12

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.3106. Min Act: -0.0001

Data Index: 240687 (C4 (Web Text))

Max Activating Token Index: 453

Text #13

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.2938. Min Act: -0.0001

Data Index: 58668 (C4 (Web Text))

Max Activating Token Index: 1002

Text #14

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.3025. Min Act: -0.0001

Data Index: 72573 (C4 (Web Text))

Max Activating Token Index: 907

Text #15

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.3123. Min Act: -0.0001

Data Index: 740839 (C4 (Web Text))

Max Activating Token Index: 950

Text #16

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.3016. Min Act: -0.0001

Data Index: 154740 (C4 (Web Text))

Max Activating Token Index: 86

Text #17

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.3094. Min Act: -0.0001

Data Index: 1237959 (C4 (Web Text))

Max Activating Token Index: 186

Text #18

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.3086. Min Act: -0.0000

Data Index: 310542 (C4 (Web Text))

Max Activating Token Index: 444

Text #19

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.3054. Min Act: -0.0001

Data Index: 542714 (C4 (Web Text))

Max Activating Token Index: 926