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

Dataset: The Pile

Neuron 984 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: 1.0236. Min Range: -1.0236

Max Act: 1.0236. Min Act: -0.0000

Data Index: 608438 (The Pile)

Max Activating Token Index: 1010

Text #1

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.6632. Min Act: -0.0000

Data Index: 1899111 (The Pile)

Max Activating Token Index: 883

Text #2

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.6663. Min Act: -0.0000

Data Index: 493688 (The Pile)

Max Activating Token Index: 945

Text #3

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.6407. Min Act: -0.0000

Data Index: 1305091 (The Pile)

Max Activating Token Index: 678

Text #4

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.6783. Min Act: -0.0000

Data Index: 701422 (The Pile)

Max Activating Token Index: 450

Text #5

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.6620. Min Act: -0.0000

Data Index: 1121951 (The Pile)

Max Activating Token Index: 542

Text #6

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.6395. Min Act: -0.0000

Data Index: 1634719 (The Pile)

Max Activating Token Index: 761

Text #7

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.5944. Min Act: -0.0000

Data Index: 745687 (The Pile)

Max Activating Token Index: 595

Text #8

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.6305. Min Act: -0.0000

Data Index: 1357759 (The Pile)

Max Activating Token Index: 386

Text #9

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.6533. Min Act: -0.0000

Data Index: 1693487 (The Pile)

Max Activating Token Index: 239

Text #10

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.6290. Min Act: -0.0000

Data Index: 817361 (The Pile)

Max Activating Token Index: 807

Text #11

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.5554. Min Act: -0.0000

Data Index: 359351 (The Pile)

Max Activating Token Index: 545

Text #12

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.5847. Min Act: -0.0000

Data Index: 1163372 (The Pile)

Max Activating Token Index: 208

Text #13

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.6300. Min Act: -0.0000

Data Index: 1828702 (The Pile)

Max Activating Token Index: 745

Text #14

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.6143. Min Act: -0.0000

Data Index: 1954469 (The Pile)

Max Activating Token Index: 787

Text #15

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.5458. Min Act: -0.0000

Data Index: 394866 (The Pile)

Max Activating Token Index: 221

Text #16

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.5947. Min Act: -0.0000

Data Index: 1054954 (The Pile)

Max Activating Token Index: 126

Text #17

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.6121. Min Act: -0.0000

Data Index: 784009 (The Pile)

Max Activating Token Index: 205

Text #18

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.6048. Min Act: -0.0000

Data Index: 893980 (The Pile)

Max Activating Token Index: 515

Text #19

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.5551. Min Act: -0.0000

Data Index: 454796 (The Pile)

Max Activating Token Index: 294