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

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

Neuron 4218 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3450. Min Range: -1.3450

Max Act: 1.3450. Min Act: -0.0000

Data Index: 549630 (C4 (Web Text))

Max Activating Token Index: 491

Text #1

Max Range: 1.3450. Min Range: -1.3450

Max Act: 1.2656. Min Act: -0.0000

Data Index: 554528 (C4 (Web Text))

Max Activating Token Index: 745

Text #2

Max Range: 1.3450. Min Range: -1.3450

Max Act: 1.1041. Min Act: -0.0000

Data Index: 347410 (C4 (Web Text))

Max Activating Token Index: 394

Text #3

Max Range: 1.3450. Min Range: -1.3450

Max Act: 1.0979. Min Act: -0.0000

Data Index: 852230 (C4 (Web Text))

Max Activating Token Index: 660

Text #4

Max Range: 1.3450. Min Range: -1.3450

Max Act: 1.1103. Min Act: -0.0000

Data Index: 62963 (C4 (Web Text))

Max Activating Token Index: 722

Text #5

Max Range: 1.3450. Min Range: -1.3450

Max Act: 1.0362. Min Act: -0.0000

Data Index: 472500 (C4 (Web Text))

Max Activating Token Index: 499

Text #6

Max Range: 1.3450. Min Range: -1.3450

Max Act: 0.9920. Min Act: -0.0000

Data Index: 1247622 (C4 (Web Text))

Max Activating Token Index: 854

Text #7

Max Range: 1.3450. Min Range: -1.3450

Max Act: 1.0372. Min Act: -0.0000

Data Index: 423155 (C4 (Web Text))

Max Activating Token Index: 885

Text #8

Max Range: 1.3450. Min Range: -1.3450

Max Act: 0.9919. Min Act: -0.0000

Data Index: 1005916 (C4 (Web Text))

Max Activating Token Index: 823

Text #9

Max Range: 1.3450. Min Range: -1.3450

Max Act: 0.9174. Min Act: -0.0000

Data Index: 379800 (C4 (Web Text))

Max Activating Token Index: 81

Text #10

Max Range: 1.3450. Min Range: -1.3450

Max Act: 0.9328. Min Act: -0.0000

Data Index: 1346376 (C4 (Web Text))

Max Activating Token Index: 763

Text #11

Max Range: 1.3450. Min Range: -1.3450

Max Act: 0.9137. Min Act: -0.0000

Data Index: 642039 (C4 (Web Text))

Max Activating Token Index: 938

Text #12

Max Range: 1.3450. Min Range: -1.3450

Max Act: 0.9163. Min Act: -0.0000

Data Index: 313584 (C4 (Web Text))

Max Activating Token Index: 73

Text #13

Max Range: 1.3450. Min Range: -1.3450

Max Act: 0.8129. Min Act: -0.0000

Data Index: 468823 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 1.3450. Min Range: -1.3450

Max Act: 0.9147. Min Act: -0.0000

Data Index: 87377 (C4 (Web Text))

Max Activating Token Index: 148

Text #15

Max Range: 1.3450. Min Range: -1.3450

Max Act: 0.8808. Min Act: -0.0000

Data Index: 466511 (C4 (Web Text))

Max Activating Token Index: 86

Text #16

Max Range: 1.3450. Min Range: -1.3450

Max Act: 0.8637. Min Act: -0.0000

Data Index: 565393 (C4 (Web Text))

Max Activating Token Index: 579

Text #17

Max Range: 1.3450. Min Range: -1.3450

Max Act: 0.9024. Min Act: -0.0000

Data Index: 207530 (C4 (Web Text))

Max Activating Token Index: 965

Text #18

Max Range: 1.3450. Min Range: -1.3450

Max Act: 0.9052. Min Act: -0.0000

Data Index: 13887 (C4 (Web Text))

Max Activating Token Index: 390

Text #19

Max Range: 1.3450. Min Range: -1.3450

Max Act: 0.8288. Min Act: -0.0000

Data Index: 177554 (C4 (Web Text))

Max Activating Token Index: 772