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

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

Neuron 4802 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9947. Min Range: -2.9947

Max Act: 2.9947. Min Act: -0.0000

Data Index: 1296886 (C4 (Web Text))

Max Activating Token Index: 723

Text #1

Max Range: 2.9947. Min Range: -2.9947

Max Act: 2.9294. Min Act: -0.0000

Data Index: 1193443 (C4 (Web Text))

Max Activating Token Index: 640

Text #2

Max Range: 2.9947. Min Range: -2.9947

Max Act: 2.7795. Min Act: -0.0000

Data Index: 493090 (C4 (Web Text))

Max Activating Token Index: 939

Text #3

Max Range: 2.9947. Min Range: -2.9947

Max Act: 2.7622. Min Act: -0.0000

Data Index: 452538 (C4 (Web Text))

Max Activating Token Index: 644

Text #4

Max Range: 2.9947. Min Range: -2.9947

Max Act: 2.5340. Min Act: -0.0000

Data Index: 293082 (C4 (Web Text))

Max Activating Token Index: 841

Text #5

Max Range: 2.9947. Min Range: -2.9947

Max Act: 2.6515. Min Act: -0.0000

Data Index: 628542 (C4 (Web Text))

Max Activating Token Index: 736

Text #6

Max Range: 2.9947. Min Range: -2.9947

Max Act: 2.6362. Min Act: 0.0000

Data Index: 1010178 (C4 (Web Text))

Max Activating Token Index: 77

Text #7

Max Range: 2.9947. Min Range: -2.9947

Max Act: 2.4566. Min Act: -0.0000

Data Index: 597761 (C4 (Web Text))

Max Activating Token Index: 126

Text #8

Max Range: 2.9947. Min Range: -2.9947

Max Act: 2.4552. Min Act: -0.0000

Data Index: 1188149 (C4 (Web Text))

Max Activating Token Index: 672

Text #9

Max Range: 2.9947. Min Range: -2.9947

Max Act: 2.3547. Min Act: -0.0000

Data Index: 754682 (C4 (Web Text))

Max Activating Token Index: 157

Text #10

Max Range: 2.9947. Min Range: -2.9947

Max Act: 2.3430. Min Act: -0.0000

Data Index: 988093 (C4 (Web Text))

Max Activating Token Index: 777

Text #11

Max Range: 2.9947. Min Range: -2.9947

Max Act: 2.3059. Min Act: -0.0000

Data Index: 92018 (C4 (Web Text))

Max Activating Token Index: 918

Text #12

Max Range: 2.9947. Min Range: -2.9947

Max Act: 2.2577. Min Act: -0.0000

Data Index: 210931 (C4 (Web Text))

Max Activating Token Index: 832

Text #13

Max Range: 2.9947. Min Range: -2.9947

Max Act: 2.2615. Min Act: -0.0000

Data Index: 498484 (C4 (Web Text))

Max Activating Token Index: 784

Text #14

Max Range: 2.9947. Min Range: -2.9947

Max Act: 2.3890. Min Act: -0.0000

Data Index: 957842 (C4 (Web Text))

Max Activating Token Index: 563

Text #15

Max Range: 2.9947. Min Range: -2.9947

Max Act: 2.2435. Min Act: -0.0000

Data Index: 885389 (C4 (Web Text))

Max Activating Token Index: 684

Text #16

Max Range: 2.9947. Min Range: -2.9947

Max Act: 2.0844. Min Act: -0.0000

Data Index: 128227 (C4 (Web Text))

Max Activating Token Index: 948

Text #17

Max Range: 2.9947. Min Range: -2.9947

Max Act: 2.3504. Min Act: -0.0000

Data Index: 1286810 (C4 (Web Text))

Max Activating Token Index: 654

Text #18

Max Range: 2.9947. Min Range: -2.9947

Max Act: 2.2001. Min Act: -0.0000

Data Index: 182099 (C4 (Web Text))

Max Activating Token Index: 210

Text #19

Max Range: 2.9947. Min Range: -2.9947

Max Act: 2.2096. Min Act: -0.0000

Data Index: 899863 (C4 (Web Text))

Max Activating Token Index: 266