Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3149 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.9652. Min Range: -3.9652

Max Act: 3.9652. Min Act: -0.0000

Data Index: 211778 (C4 (Web Text))

Max Activating Token Index: 865

Text #1

Max Range: 3.9652. Min Range: -3.9652

Max Act: 3.3343. Min Act: -0.0000

Data Index: 112699 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 3.9652. Min Range: -3.9652

Max Act: 3.3072. Min Act: -0.0000

Data Index: 527222 (C4 (Web Text))

Max Activating Token Index: 507

Text #3

Max Range: 3.9652. Min Range: -3.9652

Max Act: 3.2491. Min Act: -0.0000

Data Index: 758478 (C4 (Web Text))

Max Activating Token Index: 75

Text #4

Max Range: 3.9652. Min Range: -3.9652

Max Act: 3.0057. Min Act: -0.0000

Data Index: 909798 (C4 (Web Text))

Max Activating Token Index: 930

Text #5

Max Range: 3.9652. Min Range: -3.9652

Max Act: 2.5705. Min Act: -0.0000

Data Index: 37282 (C4 (Web Text))

Max Activating Token Index: 102

Text #6

Max Range: 3.9652. Min Range: -3.9652

Max Act: 2.5436. Min Act: -0.0001

Data Index: 1215076 (C4 (Web Text))

Max Activating Token Index: 1004

Text #7

Max Range: 3.9652. Min Range: -3.9652

Max Act: 2.6535. Min Act: -0.0000

Data Index: 317683 (C4 (Web Text))

Max Activating Token Index: 236

Text #8

Max Range: 3.9652. Min Range: -3.9652

Max Act: 2.5990. Min Act: -0.0001

Data Index: 121567 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 3.9652. Min Range: -3.9652

Max Act: 2.5559. Min Act: -0.0000

Data Index: 1002626 (C4 (Web Text))

Max Activating Token Index: 406

Text #10

Max Range: 3.9652. Min Range: -3.9652

Max Act: 2.5022. Min Act: -0.0000

Data Index: 741122 (C4 (Web Text))

Max Activating Token Index: 51

Text #11

Max Range: 3.9652. Min Range: -3.9652

Max Act: 2.3684. Min Act: -0.0000

Data Index: 1097402 (C4 (Web Text))

Max Activating Token Index: 422

Text #12

Max Range: 3.9652. Min Range: -3.9652

Max Act: 2.3736. Min Act: -0.0000

Data Index: 790115 (C4 (Web Text))

Max Activating Token Index: 94

Text #13

Max Range: 3.9652. Min Range: -3.9652

Max Act: 2.6174. Min Act: -0.0000

Data Index: 287709 (C4 (Web Text))

Max Activating Token Index: 1005

Text #14

Max Range: 3.9652. Min Range: -3.9652

Max Act: 2.7330. Min Act: -0.0000

Data Index: 830453 (C4 (Web Text))

Max Activating Token Index: 150

Text #15

Max Range: 3.9652. Min Range: -3.9652

Max Act: 2.3116. Min Act: -0.0000

Data Index: 1251964 (C4 (Web Text))

Max Activating Token Index: 439

Text #16

Max Range: 3.9652. Min Range: -3.9652

Max Act: 2.4263. Min Act: -0.0000

Data Index: 658080 (C4 (Web Text))

Max Activating Token Index: 990

Text #17

Max Range: 3.9652. Min Range: -3.9652

Max Act: 2.4096. Min Act: -0.0000

Data Index: 223447 (C4 (Web Text))

Max Activating Token Index: 729

Text #18

Max Range: 3.9652. Min Range: -3.9652

Max Act: 2.4080. Min Act: -0.0000

Data Index: 240440 (C4 (Web Text))

Max Activating Token Index: 446

Text #19

Max Range: 3.9652. Min Range: -3.9652

Max Act: 2.4108. Min Act: -0.0000

Data Index: 1151114 (C4 (Web Text))

Max Activating Token Index: 532