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

Dataset: The Pile

Neuron 2532 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8495. Min Range: -3.8495

Max Act: 3.8495. Min Act: -0.0000

Data Index: 207101 (The Pile)

Max Activating Token Index: 557

Text #1

Max Range: 3.8495. Min Range: -3.8495

Max Act: 3.3861. Min Act: -0.0000

Data Index: 1527417 (The Pile)

Max Activating Token Index: 290

Text #2

Max Range: 3.8495. Min Range: -3.8495

Max Act: 3.5697. Min Act: -0.0000

Data Index: 698555 (The Pile)

Max Activating Token Index: 210

Text #3

Max Range: 3.8495. Min Range: -3.8495

Max Act: 3.3156. Min Act: -0.0000

Data Index: 1516450 (The Pile)

Max Activating Token Index: 915

Text #4

Max Range: 3.8495. Min Range: -3.8495

Max Act: 3.3191. Min Act: -0.0000

Data Index: 1027553 (The Pile)

Max Activating Token Index: 342

Text #5

Max Range: 3.8495. Min Range: -3.8495

Max Act: 3.3481. Min Act: -0.0000

Data Index: 774298 (The Pile)

Max Activating Token Index: 412

Text #6

Max Range: 3.8495. Min Range: -3.8495

Max Act: 3.2822. Min Act: -0.0000

Data Index: 186630 (The Pile)

Max Activating Token Index: 564

Text #7

Max Range: 3.8495. Min Range: -3.8495

Max Act: 2.9351. Min Act: -0.0000

Data Index: 259525 (The Pile)

Max Activating Token Index: 983

Text #8

Max Range: 3.8495. Min Range: -3.8495

Max Act: 3.3654. Min Act: -0.0000

Data Index: 931114 (The Pile)

Max Activating Token Index: 782

Text #9

Max Range: 3.8495. Min Range: -3.8495

Max Act: 3.1376. Min Act: -0.0000

Data Index: 1287386 (The Pile)

Max Activating Token Index: 369

Text #10

Max Range: 3.8495. Min Range: -3.8495

Max Act: 2.8126. Min Act: -0.0000

Data Index: 966139 (The Pile)

Max Activating Token Index: 366

Text #11

Max Range: 3.8495. Min Range: -3.8495

Max Act: 2.8161. Min Act: -0.0000

Data Index: 528843 (The Pile)

Max Activating Token Index: 572

Text #12

Max Range: 3.8495. Min Range: -3.8495

Max Act: 2.7650. Min Act: -0.0000

Data Index: 1140278 (The Pile)

Max Activating Token Index: 643

Text #13

Max Range: 3.8495. Min Range: -3.8495

Max Act: 2.7507. Min Act: -0.0000

Data Index: 955599 (The Pile)

Max Activating Token Index: 576

Text #14

Max Range: 3.8495. Min Range: -3.8495

Max Act: 2.9785. Min Act: -0.0000

Data Index: 1133641 (The Pile)

Max Activating Token Index: 447

Text #15

Max Range: 3.8495. Min Range: -3.8495

Max Act: 2.9877. Min Act: -0.0000

Data Index: 40923 (The Pile)

Max Activating Token Index: 69

Text #16

Max Range: 3.8495. Min Range: -3.8495

Max Act: 2.8486. Min Act: -0.0000

Data Index: 444540 (The Pile)

Max Activating Token Index: 101

Text #17

Max Range: 3.8495. Min Range: -3.8495

Max Act: 2.8508. Min Act: -0.0000

Data Index: 28662 (The Pile)

Max Activating Token Index: 67

Text #18

Max Range: 3.8495. Min Range: -3.8495

Max Act: 2.5713. Min Act: -0.0000

Data Index: 1178138 (The Pile)

Max Activating Token Index: 766

Text #19

Max Range: 3.8495. Min Range: -3.8495

Max Act: 2.5519. Min Act: -0.0000

Data Index: 1746879 (The Pile)

Max Activating Token Index: 809