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

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

Neuron 1485 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1947. Min Range: -3.1947

Max Act: 3.1947. Min Act: -0.0000

Data Index: 1260684 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 3.1947. Min Range: -3.1947

Max Act: 2.7667. Min Act: -0.0000

Data Index: 1055672 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 3.1947. Min Range: -3.1947

Max Act: 2.7193. Min Act: -0.0000

Data Index: 235676 (C4 (Web Text))

Max Activating Token Index: 466

Text #3

Max Range: 3.1947. Min Range: -3.1947

Max Act: 2.5506. Min Act: -0.0000

Data Index: 2853 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 3.1947. Min Range: -3.1947

Max Act: 2.4665. Min Act: -0.0000

Data Index: 427916 (C4 (Web Text))

Max Activating Token Index: 990

Text #5

Max Range: 3.1947. Min Range: -3.1947

Max Act: 2.7328. Min Act: -0.0000

Data Index: 776098 (C4 (Web Text))

Max Activating Token Index: 140

Text #6

Max Range: 3.1947. Min Range: -3.1947

Max Act: 2.5290. Min Act: -0.0000

Data Index: 1331245 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 3.1947. Min Range: -3.1947

Max Act: 2.6777. Min Act: -0.0000

Data Index: 50983 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 3.1947. Min Range: -3.1947

Max Act: 2.4998. Min Act: -0.0000

Data Index: 988685 (C4 (Web Text))

Max Activating Token Index: 1018

Text #9

Max Range: 3.1947. Min Range: -3.1947

Max Act: 2.4668. Min Act: -0.0000

Data Index: 14641 (C4 (Web Text))

Max Activating Token Index: 6

Text #10

Max Range: 3.1947. Min Range: -3.1947

Max Act: 2.4163. Min Act: -0.0000

Data Index: 517728 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 3.1947. Min Range: -3.1947

Max Act: 2.3948. Min Act: -0.0000

Data Index: 417267 (C4 (Web Text))

Max Activating Token Index: 9

Text #12

Max Range: 3.1947. Min Range: -3.1947

Max Act: 2.3003. Min Act: -0.0000

Data Index: 998235 (C4 (Web Text))

Max Activating Token Index: 7

Text #13

Max Range: 3.1947. Min Range: -3.1947

Max Act: 2.2997. Min Act: -0.0000

Data Index: 520124 (C4 (Web Text))

Max Activating Token Index: 10

Text #14

Max Range: 3.1947. Min Range: -3.1947

Max Act: 2.2748. Min Act: -0.0000

Data Index: 920633 (C4 (Web Text))

Max Activating Token Index: 8

Text #15

Max Range: 3.1947. Min Range: -3.1947

Max Act: 2.3861. Min Act: -0.0000

Data Index: 500260 (C4 (Web Text))

Max Activating Token Index: 5

Text #16

Max Range: 3.1947. Min Range: -3.1947

Max Act: 2.0696. Min Act: -0.0000

Data Index: 1138893 (C4 (Web Text))

Max Activating Token Index: 32

Text #17

Max Range: 3.1947. Min Range: -3.1947

Max Act: 2.1762. Min Act: -0.0000

Data Index: 68950 (C4 (Web Text))

Max Activating Token Index: 9

Text #18

Max Range: 3.1947. Min Range: -3.1947

Max Act: 2.2156. Min Act: -0.0000

Data Index: 1082203 (C4 (Web Text))

Max Activating Token Index: 833

Text #19

Max Range: 3.1947. Min Range: -3.1947

Max Act: 2.1637. Min Act: -0.0000

Data Index: 644696 (C4 (Web Text))

Max Activating Token Index: 463