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

Dataset: The Pile

Neuron 1681 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.8924. Min Act: -0.0000

Data Index: 56715 (The Pile)

Max Activating Token Index: 457

Text #1

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.8374. Min Act: -0.0000

Data Index: 1462617 (The Pile)

Max Activating Token Index: 508

Text #2

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.8226. Min Act: -0.0000

Data Index: 212781 (The Pile)

Max Activating Token Index: 183

Text #3

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.7926. Min Act: -0.0000

Data Index: 32888 (The Pile)

Max Activating Token Index: 207

Text #4

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.7428. Min Act: -0.0000

Data Index: 1075375 (The Pile)

Max Activating Token Index: 204

Text #5

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.7891. Min Act: -0.0000

Data Index: 960123 (The Pile)

Max Activating Token Index: 228

Text #6

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.8028. Min Act: -0.0000

Data Index: 1528554 (The Pile)

Max Activating Token Index: 133

Text #7

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.7815. Min Act: -0.0001

Data Index: 1461794 (The Pile)

Max Activating Token Index: 934

Text #8

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.7969. Min Act: -0.0001

Data Index: 152628 (The Pile)

Max Activating Token Index: 181

Text #9

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.7656. Min Act: -0.0000

Data Index: 1073740 (The Pile)

Max Activating Token Index: 330

Text #10

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.7806. Min Act: -0.0001

Data Index: 416257 (The Pile)

Max Activating Token Index: 283

Text #11

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.7996. Min Act: -0.0000

Data Index: 306797 (The Pile)

Max Activating Token Index: 93

Text #12

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.7756. Min Act: -0.0000

Data Index: 294216 (The Pile)

Max Activating Token Index: 149

Text #13

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.7133. Min Act: -0.0000

Data Index: 1226302 (The Pile)

Max Activating Token Index: 108

Text #14

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.7251. Min Act: -0.0000

Data Index: 97243 (The Pile)

Max Activating Token Index: 253

Text #15

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.6929. Min Act: -0.0000

Data Index: 1643069 (The Pile)

Max Activating Token Index: 482

Text #16

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.6848. Min Act: -0.0000

Data Index: 1644367 (The Pile)

Max Activating Token Index: 82

Text #17

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.6655. Min Act: -0.0000

Data Index: 1511504 (The Pile)

Max Activating Token Index: 660

Text #18

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.6787. Min Act: -0.0000

Data Index: 258799 (The Pile)

Max Activating Token Index: 63

Text #19

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.7034. Min Act: -0.0000

Data Index: 1555097 (The Pile)

Max Activating Token Index: 235