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

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

Neuron 176 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2990. Min Range: -0.2990

Max Act: 0.2990. Min Act: -0.0001

Data Index: 968342 (C4 (Web Text))

Max Activating Token Index: 1001

Text #1

Max Range: 0.2990. Min Range: -0.2990

Max Act: 0.2821. Min Act: -0.0001

Data Index: 1015607 (C4 (Web Text))

Max Activating Token Index: 935

Text #2

Max Range: 0.2990. Min Range: -0.2990

Max Act: 0.2768. Min Act: -0.0001

Data Index: 457859 (C4 (Web Text))

Max Activating Token Index: 70

Text #3

Max Range: 0.2990. Min Range: -0.2990

Max Act: 0.2660. Min Act: -0.0001

Data Index: 212025 (C4 (Web Text))

Max Activating Token Index: 53

Text #4

Max Range: 0.2990. Min Range: -0.2990

Max Act: 0.2702. Min Act: -0.0001

Data Index: 127091 (C4 (Web Text))

Max Activating Token Index: 1004

Text #5

Max Range: 0.2990. Min Range: -0.2990

Max Act: 0.2698. Min Act: -0.0001

Data Index: 429436 (C4 (Web Text))

Max Activating Token Index: 58

Text #6

Max Range: 0.2990. Min Range: -0.2990

Max Act: 0.2686. Min Act: -0.0001

Data Index: 417878 (C4 (Web Text))

Max Activating Token Index: 810

Text #7

Max Range: 0.2990. Min Range: -0.2990

Max Act: 0.2654. Min Act: -0.0001

Data Index: 189879 (C4 (Web Text))

Max Activating Token Index: 53

Text #8

Max Range: 0.2990. Min Range: -0.2990

Max Act: 0.2743. Min Act: -0.0001

Data Index: 1088454 (C4 (Web Text))

Max Activating Token Index: 1017

Text #9

Max Range: 0.2990. Min Range: -0.2990

Max Act: 0.2625. Min Act: -0.0001

Data Index: 722022 (C4 (Web Text))

Max Activating Token Index: 905

Text #10

Max Range: 0.2990. Min Range: -0.2990

Max Act: 0.2824. Min Act: -0.0001

Data Index: 322675 (C4 (Web Text))

Max Activating Token Index: 24

Text #11

Max Range: 0.2990. Min Range: -0.2990

Max Act: 0.2483. Min Act: -0.0001

Data Index: 770560 (C4 (Web Text))

Max Activating Token Index: 947

Text #12

Max Range: 0.2990. Min Range: -0.2990

Max Act: 0.2510. Min Act: -0.0001

Data Index: 118649 (C4 (Web Text))

Max Activating Token Index: 84

Text #13

Max Range: 0.2990. Min Range: -0.2990

Max Act: 0.2427. Min Act: -0.0001

Data Index: 1158784 (C4 (Web Text))

Max Activating Token Index: 84

Text #14

Max Range: 0.2990. Min Range: -0.2990

Max Act: 0.2526. Min Act: -0.0001

Data Index: 1117141 (C4 (Web Text))

Max Activating Token Index: 128

Text #15

Max Range: 0.2990. Min Range: -0.2990

Max Act: 0.2550. Min Act: -0.0001

Data Index: 384861 (C4 (Web Text))

Max Activating Token Index: 983

Text #16

Max Range: 0.2990. Min Range: -0.2990

Max Act: 0.2424. Min Act: -0.0001

Data Index: 1021523 (C4 (Web Text))

Max Activating Token Index: 941

Text #17

Max Range: 0.2990. Min Range: -0.2990

Max Act: 0.2305. Min Act: -0.0001

Data Index: 392291 (C4 (Web Text))

Max Activating Token Index: 265

Text #18

Max Range: 0.2990. Min Range: -0.2990

Max Act: 0.2487. Min Act: -0.0001

Data Index: 850169 (C4 (Web Text))

Max Activating Token Index: 39

Text #19

Max Range: 0.2990. Min Range: -0.2990

Max Act: 0.2306. Min Act: -0.0001

Data Index: 430378 (C4 (Web Text))

Max Activating Token Index: 147