Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 285 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.9263. Min Range: -1.9263

Max Act: 1.9263. Min Act: -0.0001

Data Index: 195899 (C4 (Web Text))

Max Activating Token Index: 1006

Text #1

Max Range: 1.9263. Min Range: -1.9263

Max Act: 1.7148. Min Act: -0.0001

Data Index: 83019 (C4 (Web Text))

Max Activating Token Index: 226

Text #2

Max Range: 1.9263. Min Range: -1.9263

Max Act: 1.7261. Min Act: -0.0000

Data Index: 66822 (C4 (Web Text))

Max Activating Token Index: 687

Text #3

Max Range: 1.9263. Min Range: -1.9263

Max Act: 1.5473. Min Act: -0.0001

Data Index: 180057 (C4 (Web Text))

Max Activating Token Index: 106

Text #4

Max Range: 1.9263. Min Range: -1.9263

Max Act: 1.5413. Min Act: -0.0000

Data Index: 1199085 (C4 (Web Text))

Max Activating Token Index: 88

Text #5

Max Range: 1.9263. Min Range: -1.9263

Max Act: 1.5597. Min Act: -0.0000

Data Index: 954936 (C4 (Web Text))

Max Activating Token Index: 54

Text #6

Max Range: 1.9263. Min Range: -1.9263

Max Act: 1.5497. Min Act: -0.0000

Data Index: 640699 (C4 (Web Text))

Max Activating Token Index: 101

Text #7

Max Range: 1.9263. Min Range: -1.9263

Max Act: 1.5293. Min Act: -0.0000

Data Index: 1042465 (C4 (Web Text))

Max Activating Token Index: 145

Text #8

Max Range: 1.9263. Min Range: -1.9263

Max Act: 1.3810. Min Act: -0.0001

Data Index: 466166 (C4 (Web Text))

Max Activating Token Index: 272

Text #9

Max Range: 1.9263. Min Range: -1.9263

Max Act: 1.3480. Min Act: -0.0000

Data Index: 537351 (C4 (Web Text))

Max Activating Token Index: 229

Text #10

Max Range: 1.9263. Min Range: -1.9263

Max Act: 1.3252. Min Act: -0.0000

Data Index: 763257 (C4 (Web Text))

Max Activating Token Index: 474

Text #11

Max Range: 1.9263. Min Range: -1.9263

Max Act: 1.3044. Min Act: -0.0001

Data Index: 693275 (C4 (Web Text))

Max Activating Token Index: 894

Text #12

Max Range: 1.9263. Min Range: -1.9263

Max Act: 1.3013. Min Act: -0.0000

Data Index: 1221680 (C4 (Web Text))

Max Activating Token Index: 87

Text #13

Max Range: 1.9263. Min Range: -1.9263

Max Act: 1.3051. Min Act: -0.0000

Data Index: 349769 (C4 (Web Text))

Max Activating Token Index: 144

Text #14

Max Range: 1.9263. Min Range: -1.9263

Max Act: 1.2484. Min Act: -0.0000

Data Index: 1028602 (C4 (Web Text))

Max Activating Token Index: 201

Text #15

Max Range: 1.9263. Min Range: -1.9263

Max Act: 1.2851. Min Act: -0.0001

Data Index: 252609 (C4 (Web Text))

Max Activating Token Index: 190

Text #16

Max Range: 1.9263. Min Range: -1.9263

Max Act: 1.2191. Min Act: -0.0000

Data Index: 848737 (C4 (Web Text))

Max Activating Token Index: 618

Text #17

Max Range: 1.9263. Min Range: -1.9263

Max Act: 1.2792. Min Act: -0.0000

Data Index: 916035 (C4 (Web Text))

Max Activating Token Index: 878

Text #18

Max Range: 1.9263. Min Range: -1.9263

Max Act: 1.2651. Min Act: -0.0000

Data Index: 1010606 (C4 (Web Text))

Max Activating Token Index: 52

Text #19

Max Range: 1.9263. Min Range: -1.9263

Max Act: 1.2563. Min Act: -0.0000

Data Index: 458898 (C4 (Web Text))

Max Activating Token Index: 679