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

Dataset: The Pile

Neuron 3605 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: 3.8820. Min Range: -3.8820

Max Act: 3.8820. Min Act: -0.0000

Data Index: 1269153 (The Pile)

Max Activating Token Index: 303

Text #1

Max Range: 3.8820. Min Range: -3.8820

Max Act: 3.3862. Min Act: -0.0000

Data Index: 1587347 (The Pile)

Max Activating Token Index: 928

Text #2

Max Range: 3.8820. Min Range: -3.8820

Max Act: 3.3142. Min Act: -0.0000

Data Index: 468609 (The Pile)

Max Activating Token Index: 401

Text #3

Max Range: 3.8820. Min Range: -3.8820

Max Act: 3.0143. Min Act: -0.0000

Data Index: 1520679 (The Pile)

Max Activating Token Index: 280

Text #4

Max Range: 3.8820. Min Range: -3.8820

Max Act: 3.1036. Min Act: -0.0000

Data Index: 1514929 (The Pile)

Max Activating Token Index: 240

Text #5

Max Range: 3.8820. Min Range: -3.8820

Max Act: 3.2006. Min Act: -0.0000

Data Index: 209596 (The Pile)

Max Activating Token Index: 315

Text #6

Max Range: 3.8820. Min Range: -3.8820

Max Act: 2.9357. Min Act: -0.0000

Data Index: 1512040 (The Pile)

Max Activating Token Index: 286

Text #7

Max Range: 3.8820. Min Range: -3.8820

Max Act: 2.7898. Min Act: -0.0000

Data Index: 825022 (The Pile)

Max Activating Token Index: 757

Text #8

Max Range: 3.8820. Min Range: -3.8820

Max Act: 2.6356. Min Act: -0.0000

Data Index: 540108 (The Pile)

Max Activating Token Index: 321

Text #9

Max Range: 3.8820. Min Range: -3.8820

Max Act: 2.7532. Min Act: -0.0000

Data Index: 1985166 (The Pile)

Max Activating Token Index: 52

Text #10

Max Range: 3.8820. Min Range: -3.8820

Max Act: 2.5925. Min Act: -0.0000

Data Index: 1743895 (The Pile)

Max Activating Token Index: 31

Text #11

Max Range: 3.8820. Min Range: -3.8820

Max Act: 2.4945. Min Act: -0.0000

Data Index: 368881 (The Pile)

Max Activating Token Index: 492

Text #12

Max Range: 3.8820. Min Range: -3.8820

Max Act: 2.3145. Min Act: -0.0000

Data Index: 149276 (The Pile)

Max Activating Token Index: 31

Text #13

Max Range: 3.8820. Min Range: -3.8820

Max Act: 2.5043. Min Act: -0.0000

Data Index: 1434672 (The Pile)

Max Activating Token Index: 811

Text #14

Max Range: 3.8820. Min Range: -3.8820

Max Act: 2.4239. Min Act: -0.0000

Data Index: 1318110 (The Pile)

Max Activating Token Index: 7

Text #15

Max Range: 3.8820. Min Range: -3.8820

Max Act: 2.3933. Min Act: -0.0000

Data Index: 1033597 (The Pile)

Max Activating Token Index: 41

Text #16

Max Range: 3.8820. Min Range: -3.8820

Max Act: 2.4449. Min Act: -0.0000

Data Index: 1186539 (The Pile)

Max Activating Token Index: 111

Text #17

Max Range: 3.8820. Min Range: -3.8820

Max Act: 2.2869. Min Act: -0.0000

Data Index: 463176 (The Pile)

Max Activating Token Index: 142

Text #18

Max Range: 3.8820. Min Range: -3.8820

Max Act: 2.1130. Min Act: -0.0000

Data Index: 1097681 (The Pile)

Max Activating Token Index: 167

Text #19

Max Range: 3.8820. Min Range: -3.8820

Max Act: 1.8910. Min Act: -0.0000

Data Index: 1223605 (The Pile)

Max Activating Token Index: 62