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

Dataset: The Pile

Neuron 1340 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0108. Min Act: -0.0000

Data Index: 136724 (The Pile)

Max Activating Token Index: 105

Text #1

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0071. Min Act: -0.0000

Data Index: 1551212 (The Pile)

Max Activating Token Index: 626

Text #2

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0070. Min Act: -0.0000

Data Index: 1918243 (The Pile)

Max Activating Token Index: 172

Text #3

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0069. Min Act: -0.0000

Data Index: 1326851 (The Pile)

Max Activating Token Index: 217

Text #4

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0065. Min Act: -0.0000

Data Index: 1619584 (The Pile)

Max Activating Token Index: 887

Text #5

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0056. Min Act: -0.0000

Data Index: 194659 (The Pile)

Max Activating Token Index: 1005

Text #6

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0056. Min Act: -0.0000

Data Index: 1500179 (The Pile)

Max Activating Token Index: 706

Text #7

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0065. Min Act: -0.0000

Data Index: 1179394 (The Pile)

Max Activating Token Index: 523

Text #8

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0067. Min Act: -0.0000

Data Index: 1280335 (The Pile)

Max Activating Token Index: 463

Text #9

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0035. Min Act: -0.0000

Data Index: 1606897 (The Pile)

Max Activating Token Index: 538

Text #10

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0057. Min Act: -0.0000

Data Index: 1947606 (The Pile)

Max Activating Token Index: 353

Text #11

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0042. Min Act: -0.0000

Data Index: 600944 (The Pile)

Max Activating Token Index: 495

Text #12

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0056. Min Act: -0.0000

Data Index: 1005827 (The Pile)

Max Activating Token Index: 437

Text #13

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0055. Min Act: -0.0000

Data Index: 645897 (The Pile)

Max Activating Token Index: 676

Text #14

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0038. Min Act: -0.0000

Data Index: 1241902 (The Pile)

Max Activating Token Index: 718

Text #15

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0044. Min Act: -0.0000

Data Index: 526952 (The Pile)

Max Activating Token Index: 88

Text #16

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0061. Min Act: -0.0000

Data Index: 21657 (The Pile)

Max Activating Token Index: 375

Text #17

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0041. Min Act: -0.0000

Data Index: 1689501 (The Pile)

Max Activating Token Index: 565

Text #18

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0048. Min Act: -0.0000

Data Index: 396856 (The Pile)

Max Activating Token Index: 747

Text #19

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0048. Min Act: -0.0000

Data Index: 1639173 (The Pile)

Max Activating Token Index: 570