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

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

Neuron 1113 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5472. Min Range: -1.5472

Max Act: 1.5472. Min Act: -0.0001

Data Index: 1318964 (C4 (Web Text))

Max Activating Token Index: 395

Text #1

Max Range: 1.5472. Min Range: -1.5472

Max Act: 1.4613. Min Act: -0.0001

Data Index: 995042 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 1.5472. Min Range: -1.5472

Max Act: 1.4403. Min Act: -0.0001

Data Index: 534017 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 1.5472. Min Range: -1.5472

Max Act: 1.4754. Min Act: -0.0001

Data Index: 565763 (C4 (Web Text))

Max Activating Token Index: 30

Text #4

Max Range: 1.5472. Min Range: -1.5472

Max Act: 1.3680. Min Act: -0.0001

Data Index: 1187226 (C4 (Web Text))

Max Activating Token Index: 123

Text #5

Max Range: 1.5472. Min Range: -1.5472

Max Act: 1.1935. Min Act: -0.0001

Data Index: 788772 (C4 (Web Text))

Max Activating Token Index: 126

Text #6

Max Range: 1.5472. Min Range: -1.5472

Max Act: 1.3355. Min Act: -0.0001

Data Index: 889768 (C4 (Web Text))

Max Activating Token Index: 778

Text #7

Max Range: 1.5472. Min Range: -1.5472

Max Act: 1.3184. Min Act: -0.0001

Data Index: 279981 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 1.5472. Min Range: -1.5472

Max Act: 1.2489. Min Act: -0.0001

Data Index: 827584 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 1.5472. Min Range: -1.5472

Max Act: 1.2350. Min Act: -0.0001

Data Index: 830113 (C4 (Web Text))

Max Activating Token Index: 269

Text #10

Max Range: 1.5472. Min Range: -1.5472

Max Act: 1.2666. Min Act: -0.0001

Data Index: 49556 (C4 (Web Text))

Max Activating Token Index: 383

Text #11

Max Range: 1.5472. Min Range: -1.5472

Max Act: 1.3371. Min Act: -0.0001

Data Index: 1003170 (C4 (Web Text))

Max Activating Token Index: 209

Text #12

Max Range: 1.5472. Min Range: -1.5472

Max Act: 1.1802. Min Act: -0.0001

Data Index: 802347 (C4 (Web Text))

Max Activating Token Index: 55

Text #13

Max Range: 1.5472. Min Range: -1.5472

Max Act: 1.2063. Min Act: -0.0001

Data Index: 607955 (C4 (Web Text))

Max Activating Token Index: 40

Text #14

Max Range: 1.5472. Min Range: -1.5472

Max Act: 1.1902. Min Act: -0.0001

Data Index: 750212 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 1.5472. Min Range: -1.5472

Max Act: 1.1838. Min Act: -0.0001

Data Index: 665001 (C4 (Web Text))

Max Activating Token Index: 35

Text #16

Max Range: 1.5472. Min Range: -1.5472

Max Act: 1.2236. Min Act: -0.0001

Data Index: 413561 (C4 (Web Text))

Max Activating Token Index: 84

Text #17

Max Range: 1.5472. Min Range: -1.5472

Max Act: 1.1454. Min Act: -0.0001

Data Index: 63787 (C4 (Web Text))

Max Activating Token Index: 1000

Text #18

Max Range: 1.5472. Min Range: -1.5472

Max Act: 1.1344. Min Act: -0.0001

Data Index: 732637 (C4 (Web Text))

Max Activating Token Index: 318

Text #19

Max Range: 1.5472. Min Range: -1.5472

Max Act: 1.1735. Min Act: -0.0001

Data Index: 148793 (C4 (Web Text))

Max Activating Token Index: 55