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

Dataset: The Pile

Neuron 1030 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6620. Min Range: -0.6620

Max Act: 0.6620. Min Act: -0.0001

Data Index: 1041609 (The Pile)

Max Activating Token Index: 111

Text #1

Max Range: 0.6620. Min Range: -0.6620

Max Act: 0.5994. Min Act: -0.0000

Data Index: 468422 (The Pile)

Max Activating Token Index: 686

Text #2

Max Range: 0.6620. Min Range: -0.6620

Max Act: 0.6292. Min Act: -0.0000

Data Index: 801927 (The Pile)

Max Activating Token Index: 659

Text #3

Max Range: 0.6620. Min Range: -0.6620

Max Act: 0.5728. Min Act: -0.0000

Data Index: 749378 (The Pile)

Max Activating Token Index: 638

Text #4

Max Range: 0.6620. Min Range: -0.6620

Max Act: 0.5788. Min Act: -0.0000

Data Index: 1292813 (The Pile)

Max Activating Token Index: 715

Text #5

Max Range: 0.6620. Min Range: -0.6620

Max Act: 0.5354. Min Act: -0.0000

Data Index: 647506 (The Pile)

Max Activating Token Index: 141

Text #6

Max Range: 0.6620. Min Range: -0.6620

Max Act: 0.5600. Min Act: -0.0000

Data Index: 342531 (The Pile)

Max Activating Token Index: 209

Text #7

Max Range: 0.6620. Min Range: -0.6620

Max Act: 0.4970. Min Act: -0.0000

Data Index: 1006492 (The Pile)

Max Activating Token Index: 160

Text #8

Max Range: 0.6620. Min Range: -0.6620

Max Act: 0.4717. Min Act: -0.0000

Data Index: 1778195 (The Pile)

Max Activating Token Index: 293

Text #9

Max Range: 0.6620. Min Range: -0.6620

Max Act: 0.5038. Min Act: -0.0000

Data Index: 967518 (The Pile)

Max Activating Token Index: 508

Text #10

Max Range: 0.6620. Min Range: -0.6620

Max Act: 0.4958. Min Act: -0.0000

Data Index: 1928099 (The Pile)

Max Activating Token Index: 162

Text #11

Max Range: 0.6620. Min Range: -0.6620

Max Act: 0.4803. Min Act: -0.0000

Data Index: 1078764 (The Pile)

Max Activating Token Index: 374

Text #12

Max Range: 0.6620. Min Range: -0.6620

Max Act: 0.5443. Min Act: -0.0001

Data Index: 620167 (The Pile)

Max Activating Token Index: 332

Text #13

Max Range: 0.6620. Min Range: -0.6620

Max Act: 0.4594. Min Act: -0.0000

Data Index: 698027 (The Pile)

Max Activating Token Index: 259

Text #14

Max Range: 0.6620. Min Range: -0.6620

Max Act: 0.5110. Min Act: -0.0000

Data Index: 161875 (The Pile)

Max Activating Token Index: 14

Text #15

Max Range: 0.6620. Min Range: -0.6620

Max Act: 0.5120. Min Act: -0.0000

Data Index: 1661710 (The Pile)

Max Activating Token Index: 222

Text #16

Max Range: 0.6620. Min Range: -0.6620

Max Act: 0.4863. Min Act: -0.0000

Data Index: 9312 (The Pile)

Max Activating Token Index: 139

Text #17

Max Range: 0.6620. Min Range: -0.6620

Max Act: 0.4957. Min Act: -0.0000

Data Index: 820963 (The Pile)

Max Activating Token Index: 617

Text #18

Max Range: 0.6620. Min Range: -0.6620

Max Act: 0.4774. Min Act: -0.0000

Data Index: 1307528 (The Pile)

Max Activating Token Index: 1007

Text #19

Max Range: 0.6620. Min Range: -0.6620

Max Act: 0.4585. Min Act: -0.0000

Data Index: 209061 (The Pile)

Max Activating Token Index: 578