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

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

Neuron 2435 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.8624. Min Act: -0.0001

Data Index: 489801 (C4 (Web Text))

Max Activating Token Index: 830

Text #1

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.8465. Min Act: -0.0001

Data Index: 234396 (C4 (Web Text))

Max Activating Token Index: 684

Text #2

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.8738. Min Act: -0.0001

Data Index: 485153 (C4 (Web Text))

Max Activating Token Index: 698

Text #3

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.8408. Min Act: -0.0001

Data Index: 269721 (C4 (Web Text))

Max Activating Token Index: 313

Text #4

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.7599. Min Act: -0.0001

Data Index: 823935 (C4 (Web Text))

Max Activating Token Index: 869

Text #5

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.7452. Min Act: -0.0001

Data Index: 1352843 (C4 (Web Text))

Max Activating Token Index: 870

Text #6

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.7314. Min Act: -0.0001

Data Index: 410703 (C4 (Web Text))

Max Activating Token Index: 214

Text #7

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.8058. Min Act: -0.0001

Data Index: 200529 (C4 (Web Text))

Max Activating Token Index: 627

Text #8

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.7069. Min Act: -0.0001

Data Index: 834686 (C4 (Web Text))

Max Activating Token Index: 371

Text #9

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.7434. Min Act: -0.0001

Data Index: 158767 (C4 (Web Text))

Max Activating Token Index: 758

Text #10

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.7065. Min Act: -0.0001

Data Index: 92030 (C4 (Web Text))

Max Activating Token Index: 436

Text #11

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.7253. Min Act: -0.0001

Data Index: 1026578 (C4 (Web Text))

Max Activating Token Index: 386

Text #12

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.7252. Min Act: -0.0001

Data Index: 1170751 (C4 (Web Text))

Max Activating Token Index: 359

Text #13

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.7212. Min Act: -0.0001

Data Index: 62823 (C4 (Web Text))

Max Activating Token Index: 405

Text #14

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.7132. Min Act: -0.0001

Data Index: 174606 (C4 (Web Text))

Max Activating Token Index: 380

Text #15

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.7099. Min Act: -0.0001

Data Index: 55865 (C4 (Web Text))

Max Activating Token Index: 891

Text #16

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.6578. Min Act: -0.0001

Data Index: 1044887 (C4 (Web Text))

Max Activating Token Index: 173

Text #17

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.6999. Min Act: -0.0001

Data Index: 1342383 (C4 (Web Text))

Max Activating Token Index: 483

Text #18

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.6657. Min Act: -0.0001

Data Index: 1312968 (C4 (Web Text))

Max Activating Token Index: 652

Text #19

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.6106. Min Act: -0.0001

Data Index: 566837 (C4 (Web Text))

Max Activating Token Index: 508