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

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

Neuron 3896 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: 4.3507. Min Range: -4.3507

Max Act: 4.3507. Min Act: -0.0000

Data Index: 238162 (C4 (Web Text))

Max Activating Token Index: 651

Text #1

Max Range: 4.3507. Min Range: -4.3507

Max Act: 3.6262. Min Act: -0.0000

Data Index: 1013723 (C4 (Web Text))

Max Activating Token Index: 275

Text #2

Max Range: 4.3507. Min Range: -4.3507

Max Act: 3.4958. Min Act: -0.0000

Data Index: 1064472 (C4 (Web Text))

Max Activating Token Index: 990

Text #3

Max Range: 4.3507. Min Range: -4.3507

Max Act: 3.4689. Min Act: -0.0000

Data Index: 1014297 (C4 (Web Text))

Max Activating Token Index: 35

Text #4

Max Range: 4.3507. Min Range: -4.3507

Max Act: 3.3435. Min Act: 0.0000

Data Index: 370827 (C4 (Web Text))

Max Activating Token Index: 730

Text #5

Max Range: 4.3507. Min Range: -4.3507

Max Act: 3.2178. Min Act: -0.0000

Data Index: 950735 (C4 (Web Text))

Max Activating Token Index: 937

Text #6

Max Range: 4.3507. Min Range: -4.3507

Max Act: 3.1640. Min Act: 0.0001

Data Index: 3603 (C4 (Web Text))

Max Activating Token Index: 302

Text #7

Max Range: 4.3507. Min Range: -4.3507

Max Act: 3.3159. Min Act: -0.0000

Data Index: 953600 (C4 (Web Text))

Max Activating Token Index: 989

Text #8

Max Range: 4.3507. Min Range: -4.3507

Max Act: 3.1577. Min Act: -0.0000

Data Index: 703134 (C4 (Web Text))

Max Activating Token Index: 21

Text #9

Max Range: 4.3507. Min Range: -4.3507

Max Act: 3.3083. Min Act: -0.0000

Data Index: 949111 (C4 (Web Text))

Max Activating Token Index: 184

Text #10

Max Range: 4.3507. Min Range: -4.3507

Max Act: 2.9569. Min Act: 0.0000

Data Index: 1055605 (C4 (Web Text))

Max Activating Token Index: 314

Text #11

Max Range: 4.3507. Min Range: -4.3507

Max Act: 3.0064. Min Act: -0.0000

Data Index: 1200120 (C4 (Web Text))

Max Activating Token Index: 505

Text #12

Max Range: 4.3507. Min Range: -4.3507

Max Act: 2.8584. Min Act: -0.0000

Data Index: 1284332 (C4 (Web Text))

Max Activating Token Index: 530

Text #13

Max Range: 4.3507. Min Range: -4.3507

Max Act: 2.9771. Min Act: -0.0000

Data Index: 818474 (C4 (Web Text))

Max Activating Token Index: 672

Text #14

Max Range: 4.3507. Min Range: -4.3507

Max Act: 2.8032. Min Act: -0.0000

Data Index: 757771 (C4 (Web Text))

Max Activating Token Index: 412

Text #15

Max Range: 4.3507. Min Range: -4.3507

Max Act: 2.8804. Min Act: -0.0000

Data Index: 2625 (C4 (Web Text))

Max Activating Token Index: 218

Text #16

Max Range: 4.3507. Min Range: -4.3507

Max Act: 2.6984. Min Act: -0.0000

Data Index: 742364 (C4 (Web Text))

Max Activating Token Index: 524

Text #17

Max Range: 4.3507. Min Range: -4.3507

Max Act: 2.6928. Min Act: -0.0000

Data Index: 334286 (C4 (Web Text))

Max Activating Token Index: 779

Text #18

Max Range: 4.3507. Min Range: -4.3507

Max Act: 2.8106. Min Act: -0.0000

Data Index: 883251 (C4 (Web Text))

Max Activating Token Index: 491

Text #19

Max Range: 4.3507. Min Range: -4.3507

Max Act: 2.7963. Min Act: -0.0000

Data Index: 252857 (C4 (Web Text))

Max Activating Token Index: 311