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

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

Neuron 47 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.9525. Min Act: -0.0000

Data Index: 139000 (C4 (Web Text))

Max Activating Token Index: 1005

Text #1

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.8841. Min Act: -0.0000

Data Index: 358964 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.8922. Min Act: -0.0000

Data Index: 1056688 (C4 (Web Text))

Max Activating Token Index: 21

Text #3

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.7920. Min Act: -0.0000

Data Index: 717165 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.7928. Min Act: -0.0000

Data Index: 417508 (C4 (Web Text))

Max Activating Token Index: 293

Text #5

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.7152. Min Act: -0.0000

Data Index: 1346870 (C4 (Web Text))

Max Activating Token Index: 855

Text #6

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.7559. Min Act: -0.0000

Data Index: 1274006 (C4 (Web Text))

Max Activating Token Index: 859

Text #7

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.7301. Min Act: -0.0000

Data Index: 994497 (C4 (Web Text))

Max Activating Token Index: 754

Text #8

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.7438. Min Act: -0.0000

Data Index: 1255373 (C4 (Web Text))

Max Activating Token Index: 103

Text #9

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.7071. Min Act: -0.0000

Data Index: 650577 (C4 (Web Text))

Max Activating Token Index: 27

Text #10

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.7174. Min Act: -0.0000

Data Index: 501251 (C4 (Web Text))

Max Activating Token Index: 312

Text #11

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.6879. Min Act: -0.0000

Data Index: 170339 (C4 (Web Text))

Max Activating Token Index: 113

Text #12

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.7093. Min Act: -0.0000

Data Index: 1019145 (C4 (Web Text))

Max Activating Token Index: 155

Text #13

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.7057. Min Act: -0.0000

Data Index: 994837 (C4 (Web Text))

Max Activating Token Index: 516

Text #14

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.7208. Min Act: -0.0000

Data Index: 109694 (C4 (Web Text))

Max Activating Token Index: 1006

Text #15

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.6982. Min Act: -0.0000

Data Index: 1195655 (C4 (Web Text))

Max Activating Token Index: 122

Text #16

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.7161. Min Act: -0.0000

Data Index: 85879 (C4 (Web Text))

Max Activating Token Index: 1014

Text #17

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.6866. Min Act: -0.0000

Data Index: 1168099 (C4 (Web Text))

Max Activating Token Index: 151

Text #18

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.6626. Min Act: -0.0000

Data Index: 556716 (C4 (Web Text))

Max Activating Token Index: 562

Text #19

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.6819. Min Act: -0.0000

Data Index: 409247 (C4 (Web Text))

Max Activating Token Index: 541