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

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

Neuron 3298 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9014. Min Range: -0.9014

Max Act: 0.9014. Min Act: -0.0000

Data Index: 474235 (C4 (Web Text))

Max Activating Token Index: 707

Text #1

Max Range: 0.9014. Min Range: -0.9014

Max Act: 0.7048. Min Act: -0.0000

Data Index: 980116 (C4 (Web Text))

Max Activating Token Index: 494

Text #2

Max Range: 0.9014. Min Range: -0.9014

Max Act: 0.5808. Min Act: -0.0000

Data Index: 1197651 (C4 (Web Text))

Max Activating Token Index: 121

Text #3

Max Range: 0.9014. Min Range: -0.9014

Max Act: 0.5700. Min Act: -0.0000

Data Index: 863191 (C4 (Web Text))

Max Activating Token Index: 645

Text #4

Max Range: 0.9014. Min Range: -0.9014

Max Act: 0.5377. Min Act: -0.0000

Data Index: 1310235 (C4 (Web Text))

Max Activating Token Index: 466

Text #5

Max Range: 0.9014. Min Range: -0.9014

Max Act: 0.5202. Min Act: -0.0000

Data Index: 729581 (C4 (Web Text))

Max Activating Token Index: 687

Text #6

Max Range: 0.9014. Min Range: -0.9014

Max Act: 0.5047. Min Act: -0.0000

Data Index: 821697 (C4 (Web Text))

Max Activating Token Index: 105

Text #7

Max Range: 0.9014. Min Range: -0.9014

Max Act: 0.4800. Min Act: -0.0000

Data Index: 1138271 (C4 (Web Text))

Max Activating Token Index: 268

Text #8

Max Range: 0.9014. Min Range: -0.9014

Max Act: 0.5437. Min Act: -0.0000

Data Index: 16220 (C4 (Web Text))

Max Activating Token Index: 195

Text #9

Max Range: 0.9014. Min Range: -0.9014

Max Act: 0.4763. Min Act: -0.0000

Data Index: 483649 (C4 (Web Text))

Max Activating Token Index: 578

Text #10

Max Range: 0.9014. Min Range: -0.9014

Max Act: 0.4457. Min Act: -0.0000

Data Index: 821593 (C4 (Web Text))

Max Activating Token Index: 312

Text #11

Max Range: 0.9014. Min Range: -0.9014

Max Act: 0.4508. Min Act: -0.0000

Data Index: 102410 (C4 (Web Text))

Max Activating Token Index: 899

Text #12

Max Range: 0.9014. Min Range: -0.9014

Max Act: 0.4168. Min Act: -0.0000

Data Index: 1089585 (C4 (Web Text))

Max Activating Token Index: 928

Text #13

Max Range: 0.9014. Min Range: -0.9014

Max Act: 0.4100. Min Act: -0.0000

Data Index: 471684 (C4 (Web Text))

Max Activating Token Index: 813

Text #14

Max Range: 0.9014. Min Range: -0.9014

Max Act: 0.4304. Min Act: -0.0000

Data Index: 366639 (C4 (Web Text))

Max Activating Token Index: 53

Text #15

Max Range: 0.9014. Min Range: -0.9014

Max Act: 0.4171. Min Act: -0.0000

Data Index: 68463 (C4 (Web Text))

Max Activating Token Index: 732

Text #16

Max Range: 0.9014. Min Range: -0.9014

Max Act: 0.4391. Min Act: -0.0000

Data Index: 452915 (C4 (Web Text))

Max Activating Token Index: 993

Text #17

Max Range: 0.9014. Min Range: -0.9014

Max Act: 0.4027. Min Act: -0.0000

Data Index: 525596 (C4 (Web Text))

Max Activating Token Index: 957

Text #18

Max Range: 0.9014. Min Range: -0.9014

Max Act: 0.3962. Min Act: -0.0000

Data Index: 239594 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 0.9014. Min Range: -0.9014

Max Act: 0.3992. Min Act: -0.0000

Data Index: 1271470 (C4 (Web Text))

Max Activating Token Index: 743