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

Dataset: The Pile

Neuron 3465 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.8944. Min Act: -0.0000

Data Index: 518079 (The Pile)

Max Activating Token Index: 91

Text #1

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.5716. Min Act: -0.0000

Data Index: 1330992 (The Pile)

Max Activating Token Index: 966

Text #2

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.7668. Min Act: -0.0000

Data Index: 1502057 (The Pile)

Max Activating Token Index: 3

Text #3

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.6338. Min Act: -0.0000

Data Index: 255443 (The Pile)

Max Activating Token Index: 398

Text #4

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.7828. Min Act: -0.0000

Data Index: 1130441 (The Pile)

Max Activating Token Index: 975

Text #5

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.5143. Min Act: -0.0000

Data Index: 1172020 (The Pile)

Max Activating Token Index: 961

Text #6

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.4119. Min Act: -0.0000

Data Index: 1679043 (The Pile)

Max Activating Token Index: 66

Text #7

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.4010. Min Act: -0.0000

Data Index: 1487548 (The Pile)

Max Activating Token Index: 1011

Text #8

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.5259. Min Act: -0.0000

Data Index: 285867 (The Pile)

Max Activating Token Index: 252

Text #9

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.5224. Min Act: -0.0000

Data Index: 243937 (The Pile)

Max Activating Token Index: 89

Text #10

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.5026. Min Act: -0.0000

Data Index: 1187397 (The Pile)

Max Activating Token Index: 686

Text #11

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.4101. Min Act: -0.0000

Data Index: 1726322 (The Pile)

Max Activating Token Index: 266

Text #12

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.4133. Min Act: -0.0000

Data Index: 1040863 (The Pile)

Max Activating Token Index: 511

Text #13

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.3593. Min Act: -0.0000

Data Index: 1710947 (The Pile)

Max Activating Token Index: 45

Text #14

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.3598. Min Act: -0.0000

Data Index: 572116 (The Pile)

Max Activating Token Index: 691

Text #15

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.4141. Min Act: -0.0000

Data Index: 1797976 (The Pile)

Max Activating Token Index: 188

Text #16

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.2768. Min Act: -0.0000

Data Index: 1066040 (The Pile)

Max Activating Token Index: 201

Text #17

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.3235. Min Act: -0.0000

Data Index: 137037 (The Pile)

Max Activating Token Index: 776

Text #18

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.2777. Min Act: -0.0000

Data Index: 158264 (The Pile)

Max Activating Token Index: 91

Text #19

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.1805. Min Act: -0.0000

Data Index: 692964 (The Pile)

Max Activating Token Index: 984