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

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

Neuron 3498 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3705. Min Range: -1.3705

Max Act: 1.3705. Min Act: -0.0001

Data Index: 398980 (C4 (Web Text))

Max Activating Token Index: 662

Text #1

Max Range: 1.3705. Min Range: -1.3705

Max Act: 1.1205. Min Act: -0.0001

Data Index: 499536 (C4 (Web Text))

Max Activating Token Index: 803

Text #2

Max Range: 1.3705. Min Range: -1.3705

Max Act: 1.1522. Min Act: -0.0001

Data Index: 772583 (C4 (Web Text))

Max Activating Token Index: 662

Text #3

Max Range: 1.3705. Min Range: -1.3705

Max Act: 1.1067. Min Act: -0.0001

Data Index: 686043 (C4 (Web Text))

Max Activating Token Index: 906

Text #4

Max Range: 1.3705. Min Range: -1.3705

Max Act: 0.9788. Min Act: -0.0001

Data Index: 161486 (C4 (Web Text))

Max Activating Token Index: 928

Text #5

Max Range: 1.3705. Min Range: -1.3705

Max Act: 1.1980. Min Act: -0.0001

Data Index: 667590 (C4 (Web Text))

Max Activating Token Index: 146

Text #6

Max Range: 1.3705. Min Range: -1.3705

Max Act: 1.0503. Min Act: -0.0001

Data Index: 458245 (C4 (Web Text))

Max Activating Token Index: 460

Text #7

Max Range: 1.3705. Min Range: -1.3705

Max Act: 1.0140. Min Act: -0.0001

Data Index: 333361 (C4 (Web Text))

Max Activating Token Index: 533

Text #8

Max Range: 1.3705. Min Range: -1.3705

Max Act: 1.1144. Min Act: -0.0001

Data Index: 1202779 (C4 (Web Text))

Max Activating Token Index: 985

Text #9

Max Range: 1.3705. Min Range: -1.3705

Max Act: 1.1522. Min Act: -0.0001

Data Index: 19370 (C4 (Web Text))

Max Activating Token Index: 452

Text #10

Max Range: 1.3705. Min Range: -1.3705

Max Act: 1.0547. Min Act: -0.0001

Data Index: 607219 (C4 (Web Text))

Max Activating Token Index: 893

Text #11

Max Range: 1.3705. Min Range: -1.3705

Max Act: 0.9786. Min Act: -0.0001

Data Index: 53667 (C4 (Web Text))

Max Activating Token Index: 167

Text #12

Max Range: 1.3705. Min Range: -1.3705

Max Act: 0.9495. Min Act: -0.0001

Data Index: 15532 (C4 (Web Text))

Max Activating Token Index: 70

Text #13

Max Range: 1.3705. Min Range: -1.3705

Max Act: 0.9765. Min Act: -0.0001

Data Index: 521690 (C4 (Web Text))

Max Activating Token Index: 59

Text #14

Max Range: 1.3705. Min Range: -1.3705

Max Act: 1.0035. Min Act: -0.0001

Data Index: 417762 (C4 (Web Text))

Max Activating Token Index: 79

Text #15

Max Range: 1.3705. Min Range: -1.3705

Max Act: 1.0485. Min Act: -0.0001

Data Index: 276277 (C4 (Web Text))

Max Activating Token Index: 552

Text #16

Max Range: 1.3705. Min Range: -1.3705

Max Act: 1.0520. Min Act: -0.0001

Data Index: 1545130 (Python Code)

Max Activating Token Index: 927

Text #17

Max Range: 1.3705. Min Range: -1.3705

Max Act: 0.9805. Min Act: -0.0001

Data Index: 37696 (C4 (Web Text))

Max Activating Token Index: 23

Text #18

Max Range: 1.3705. Min Range: -1.3705

Max Act: 0.9838. Min Act: -0.0001

Data Index: 384734 (C4 (Web Text))

Max Activating Token Index: 876

Text #19

Max Range: 1.3705. Min Range: -1.3705

Max Act: 0.9377. Min Act: -0.0001

Data Index: 458484 (C4 (Web Text))

Max Activating Token Index: 61