Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2478 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.6840. Min Range: -0.6840

Max Act: 0.6840. Min Act: -0.0000

Data Index: 1612015 (The Pile)

Max Activating Token Index: 566

Text #1

Max Range: 0.6840. Min Range: -0.6840

Max Act: 0.6743. Min Act: -0.0001

Data Index: 342165 (The Pile)

Max Activating Token Index: 398

Text #2

Max Range: 0.6840. Min Range: -0.6840

Max Act: 0.6271. Min Act: -0.0000

Data Index: 526331 (The Pile)

Max Activating Token Index: 329

Text #3

Max Range: 0.6840. Min Range: -0.6840

Max Act: 0.6450. Min Act: -0.0000

Data Index: 761847 (The Pile)

Max Activating Token Index: 244

Text #4

Max Range: 0.6840. Min Range: -0.6840

Max Act: 0.6067. Min Act: -0.0000

Data Index: 1205250 (The Pile)

Max Activating Token Index: 957

Text #5

Max Range: 0.6840. Min Range: -0.6840

Max Act: 0.6610. Min Act: -0.0000

Data Index: 987831 (The Pile)

Max Activating Token Index: 870

Text #6

Max Range: 0.6840. Min Range: -0.6840

Max Act: 0.6361. Min Act: -0.0000

Data Index: 8651 (The Pile)

Max Activating Token Index: 242

Text #7

Max Range: 0.6840. Min Range: -0.6840

Max Act: 0.6331. Min Act: -0.0000

Data Index: 1303199 (The Pile)

Max Activating Token Index: 124

Text #8

Max Range: 0.6840. Min Range: -0.6840

Max Act: 0.6145. Min Act: -0.0000

Data Index: 1558855 (The Pile)

Max Activating Token Index: 973

Text #9

Max Range: 0.6840. Min Range: -0.6840

Max Act: 0.6338. Min Act: -0.0000

Data Index: 1291619 (The Pile)

Max Activating Token Index: 510

Text #10

Max Range: 0.6840. Min Range: -0.6840

Max Act: 0.6413. Min Act: -0.0000

Data Index: 100266 (The Pile)

Max Activating Token Index: 93

Text #11

Max Range: 0.6840. Min Range: -0.6840

Max Act: 0.5992. Min Act: -0.0000

Data Index: 1756538 (The Pile)

Max Activating Token Index: 800

Text #12

Max Range: 0.6840. Min Range: -0.6840

Max Act: 0.5534. Min Act: -0.0000

Data Index: 259112 (The Pile)

Max Activating Token Index: 776

Text #13

Max Range: 0.6840. Min Range: -0.6840

Max Act: 0.5461. Min Act: -0.0000

Data Index: 224339 (The Pile)

Max Activating Token Index: 1007

Text #14

Max Range: 0.6840. Min Range: -0.6840

Max Act: 0.5823. Min Act: -0.0000

Data Index: 1353947 (The Pile)

Max Activating Token Index: 159

Text #15

Max Range: 0.6840. Min Range: -0.6840

Max Act: 0.5965. Min Act: -0.0000

Data Index: 293033 (The Pile)

Max Activating Token Index: 543

Text #16

Max Range: 0.6840. Min Range: -0.6840

Max Act: 0.5568. Min Act: -0.0000

Data Index: 1487420 (The Pile)

Max Activating Token Index: 581

Text #17

Max Range: 0.6840. Min Range: -0.6840

Max Act: 0.5681. Min Act: -0.0000

Data Index: 1699924 (The Pile)

Max Activating Token Index: 549

Text #18

Max Range: 0.6840. Min Range: -0.6840

Max Act: 0.5312. Min Act: -0.0000

Data Index: 1903002 (The Pile)

Max Activating Token Index: 251

Text #19

Max Range: 0.6840. Min Range: -0.6840

Max Act: 0.5627. Min Act: -0.0000

Data Index: 1666006 (The Pile)

Max Activating Token Index: 792