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

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

Neuron 2043 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: 0.3155. Min Range: -0.3155

Max Act: 0.3155. Min Act: -0.0001

Data Index: 543594 (C4 (Web Text))

Max Activating Token Index: 60

Text #1

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2914. Min Act: -0.0001

Data Index: 147644 (C4 (Web Text))

Max Activating Token Index: 704

Text #2

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2932. Min Act: -0.0001

Data Index: 628237 (C4 (Web Text))

Max Activating Token Index: 879

Text #3

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2848. Min Act: -0.0001

Data Index: 46841 (C4 (Web Text))

Max Activating Token Index: 710

Text #4

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2661. Min Act: -0.0001

Data Index: 361623 (C4 (Web Text))

Max Activating Token Index: 52

Text #5

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2794. Min Act: -0.0001

Data Index: 38812 (C4 (Web Text))

Max Activating Token Index: 299

Text #6

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2712. Min Act: -0.0001

Data Index: 1007803 (C4 (Web Text))

Max Activating Token Index: 209

Text #7

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2653. Min Act: -0.0001

Data Index: 459489 (C4 (Web Text))

Max Activating Token Index: 50

Text #8

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2624. Min Act: -0.0001

Data Index: 1080670 (C4 (Web Text))

Max Activating Token Index: 947

Text #9

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2560. Min Act: -0.0000

Data Index: 74999 (C4 (Web Text))

Max Activating Token Index: 909

Text #10

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2623. Min Act: -0.0001

Data Index: 1099102 (C4 (Web Text))

Max Activating Token Index: 971

Text #11

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2542. Min Act: -0.0001

Data Index: 625938 (C4 (Web Text))

Max Activating Token Index: 521

Text #12

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2636. Min Act: -0.0001

Data Index: 742173 (C4 (Web Text))

Max Activating Token Index: 99

Text #13

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2584. Min Act: -0.0000

Data Index: 811189 (C4 (Web Text))

Max Activating Token Index: 458

Text #14

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2665. Min Act: 0.0000

Data Index: 662151 (C4 (Web Text))

Max Activating Token Index: 150

Text #15

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2609. Min Act: -0.0000

Data Index: 157891 (C4 (Web Text))

Max Activating Token Index: 633

Text #16

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2618. Min Act: -0.0001

Data Index: 1002542 (C4 (Web Text))

Max Activating Token Index: 285

Text #17

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2593. Min Act: 0.0000

Data Index: 633508 (C4 (Web Text))

Max Activating Token Index: 260

Text #18

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2441. Min Act: -0.0001

Data Index: 449673 (C4 (Web Text))

Max Activating Token Index: 751

Text #19

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2516. Min Act: -0.0001

Data Index: 363351 (C4 (Web Text))

Max Activating Token Index: 788