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

Dataset: The Pile

Neuron 2393 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0158. Min Act: -0.0000

Data Index: 1622829 (The Pile)

Max Activating Token Index: 694

Text #1

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0154. Min Act: -0.0000

Data Index: 1104904 (The Pile)

Max Activating Token Index: 668

Text #2

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0156. Min Act: -0.0000

Data Index: 1537364 (The Pile)

Max Activating Token Index: 620

Text #3

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0152. Min Act: -0.0000

Data Index: 1366703 (The Pile)

Max Activating Token Index: 561

Text #4

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0150. Min Act: -0.0000

Data Index: 40563 (The Pile)

Max Activating Token Index: 600

Text #5

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0149. Min Act: -0.0000

Data Index: 1820935 (The Pile)

Max Activating Token Index: 720

Text #6

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0148. Min Act: -0.0000

Data Index: 352479 (The Pile)

Max Activating Token Index: 704

Text #7

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0146. Min Act: -0.0000

Data Index: 557071 (The Pile)

Max Activating Token Index: 690

Text #8

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0145. Min Act: -0.0000

Data Index: 1427636 (The Pile)

Max Activating Token Index: 542

Text #9

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0145. Min Act: -0.0000

Data Index: 1430954 (The Pile)

Max Activating Token Index: 860

Text #10

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0145. Min Act: -0.0000

Data Index: 918702 (The Pile)

Max Activating Token Index: 857

Text #11

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0144. Min Act: -0.0000

Data Index: 450819 (The Pile)

Max Activating Token Index: 592

Text #12

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0143. Min Act: -0.0000

Data Index: 1336138 (The Pile)

Max Activating Token Index: 720

Text #13

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0143. Min Act: -0.0001

Data Index: 1230565 (The Pile)

Max Activating Token Index: 603

Text #14

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0143. Min Act: -0.0000

Data Index: 515165 (The Pile)

Max Activating Token Index: 661

Text #15

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0142. Min Act: -0.0000

Data Index: 1233712 (The Pile)

Max Activating Token Index: 817

Text #16

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0142. Min Act: -0.0000

Data Index: 445919 (The Pile)

Max Activating Token Index: 693

Text #17

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0141. Min Act: -0.0000

Data Index: 1904597 (The Pile)

Max Activating Token Index: 587

Text #18

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0141. Min Act: -0.0000

Data Index: 1584889 (The Pile)

Max Activating Token Index: 581

Text #19

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0138. Min Act: -0.0000

Data Index: 1287254 (The Pile)

Max Activating Token Index: 515