Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1484 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.5917. Min Act: -0.0001

Data Index: 1558890 (Python Code)

Max Activating Token Index: 710

Text #1

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.5440. Min Act: -0.0001

Data Index: 1462004 (Python Code)

Max Activating Token Index: 143

Text #2

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.6226. Min Act: -0.0001

Data Index: 1096767 (C4 (Web Text))

Max Activating Token Index: 87

Text #3

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.5778. Min Act: -0.0001

Data Index: 820538 (C4 (Web Text))

Max Activating Token Index: 88

Text #4

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.5781. Min Act: -0.0001

Data Index: 245152 (C4 (Web Text))

Max Activating Token Index: 193

Text #5

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.5742. Min Act: -0.0001

Data Index: 65007 (C4 (Web Text))

Max Activating Token Index: 206

Text #6

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.5458. Min Act: -0.0001

Data Index: 1316185 (C4 (Web Text))

Max Activating Token Index: 97

Text #7

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.5060. Min Act: -0.0001

Data Index: 1374314 (Python Code)

Max Activating Token Index: 994

Text #8

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.5647. Min Act: -0.0001

Data Index: 1170419 (C4 (Web Text))

Max Activating Token Index: 73

Text #9

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.5551. Min Act: -0.0001

Data Index: 276984 (C4 (Web Text))

Max Activating Token Index: 148

Text #10

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.5188. Min Act: -0.0000

Data Index: 1557106 (Python Code)

Max Activating Token Index: 845

Text #11

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.5298. Min Act: -0.0001

Data Index: 1378024 (Python Code)

Max Activating Token Index: 653

Text #12

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.4901. Min Act: -0.0000

Data Index: 1582097 (Python Code)

Max Activating Token Index: 1020

Text #13

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.5256. Min Act: -0.0001

Data Index: 1656438 (Python Code)

Max Activating Token Index: 245

Text #14

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.5501. Min Act: -0.0001

Data Index: 1542144 (Python Code)

Max Activating Token Index: 626

Text #15

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.4967. Min Act: -0.0001

Data Index: 176975 (C4 (Web Text))

Max Activating Token Index: 929

Text #16

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.5172. Min Act: -0.0001

Data Index: 684501 (C4 (Web Text))

Max Activating Token Index: 417

Text #17

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.4970. Min Act: -0.0001

Data Index: 1362329 (Python Code)

Max Activating Token Index: 819

Text #18

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.5410. Min Act: -0.0001

Data Index: 1468089 (Python Code)

Max Activating Token Index: 878

Text #19

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.4652. Min Act: -0.0001

Data Index: 1466238 (Python Code)

Max Activating Token Index: 514