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

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

Neuron 1462 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7127. Min Range: -4.7127

Max Act: 4.7127. Min Act: -0.0000

Data Index: 919839 (C4 (Web Text))

Max Activating Token Index: 455

Text #1

Max Range: 4.7127. Min Range: -4.7127

Max Act: 3.9002. Min Act: -0.0001

Data Index: 70328 (C4 (Web Text))

Max Activating Token Index: 110

Text #2

Max Range: 4.7127. Min Range: -4.7127

Max Act: 3.6131. Min Act: -0.0001

Data Index: 620340 (C4 (Web Text))

Max Activating Token Index: 1007

Text #3

Max Range: 4.7127. Min Range: -4.7127

Max Act: 3.6870. Min Act: -0.0001

Data Index: 870363 (C4 (Web Text))

Max Activating Token Index: 441

Text #4

Max Range: 4.7127. Min Range: -4.7127

Max Act: 3.2905. Min Act: -0.0000

Data Index: 881594 (C4 (Web Text))

Max Activating Token Index: 852

Text #5

Max Range: 4.7127. Min Range: -4.7127

Max Act: 3.2180. Min Act: -0.0001

Data Index: 1118670 (C4 (Web Text))

Max Activating Token Index: 99

Text #6

Max Range: 4.7127. Min Range: -4.7127

Max Act: 3.0799. Min Act: -0.0001

Data Index: 101685 (C4 (Web Text))

Max Activating Token Index: 317

Text #7

Max Range: 4.7127. Min Range: -4.7127

Max Act: 2.7376. Min Act: -0.0001

Data Index: 895061 (C4 (Web Text))

Max Activating Token Index: 311

Text #8

Max Range: 4.7127. Min Range: -4.7127

Max Act: 3.0777. Min Act: -0.0001

Data Index: 46903 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 4.7127. Min Range: -4.7127

Max Act: 2.9201. Min Act: -0.0001

Data Index: 958675 (C4 (Web Text))

Max Activating Token Index: 78

Text #10

Max Range: 4.7127. Min Range: -4.7127

Max Act: 2.8210. Min Act: -0.0001

Data Index: 737807 (C4 (Web Text))

Max Activating Token Index: 873

Text #11

Max Range: 4.7127. Min Range: -4.7127

Max Act: 3.1743. Min Act: -0.0001

Data Index: 638649 (C4 (Web Text))

Max Activating Token Index: 139

Text #12

Max Range: 4.7127. Min Range: -4.7127

Max Act: 2.9352. Min Act: -0.0001

Data Index: 489157 (C4 (Web Text))

Max Activating Token Index: 77

Text #13

Max Range: 4.7127. Min Range: -4.7127

Max Act: 2.8260. Min Act: -0.0001

Data Index: 656334 (C4 (Web Text))

Max Activating Token Index: 907

Text #14

Max Range: 4.7127. Min Range: -4.7127

Max Act: 2.7775. Min Act: -0.0001

Data Index: 222434 (C4 (Web Text))

Max Activating Token Index: 202

Text #15

Max Range: 4.7127. Min Range: -4.7127

Max Act: 2.7900. Min Act: -0.0001

Data Index: 141135 (C4 (Web Text))

Max Activating Token Index: 832

Text #16

Max Range: 4.7127. Min Range: -4.7127

Max Act: 2.7887. Min Act: -0.0001

Data Index: 723965 (C4 (Web Text))

Max Activating Token Index: 141

Text #17

Max Range: 4.7127. Min Range: -4.7127

Max Act: 2.9439. Min Act: -0.0000

Data Index: 406110 (C4 (Web Text))

Max Activating Token Index: 848

Text #18

Max Range: 4.7127. Min Range: -4.7127

Max Act: 2.8272. Min Act: -0.0000

Data Index: 47111 (C4 (Web Text))

Max Activating Token Index: 455

Text #19

Max Range: 4.7127. Min Range: -4.7127

Max Act: 2.7969. Min Act: -0.0001

Data Index: 694264 (C4 (Web Text))

Max Activating Token Index: 828