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

Dataset: The Pile

Neuron 39 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.4861. Min Act: -0.0000

Data Index: 598170 (The Pile)

Max Activating Token Index: 104

Text #1

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.3960. Min Act: -0.0000

Data Index: 707587 (The Pile)

Max Activating Token Index: 363

Text #2

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.3928. Min Act: -0.0000

Data Index: 1524211 (The Pile)

Max Activating Token Index: 328

Text #3

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.3898. Min Act: -0.0000

Data Index: 1117951 (The Pile)

Max Activating Token Index: 156

Text #4

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.3878. Min Act: -0.0000

Data Index: 1694508 (The Pile)

Max Activating Token Index: 458

Text #5

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.3681. Min Act: -0.0000

Data Index: 779582 (The Pile)

Max Activating Token Index: 482

Text #6

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.3516. Min Act: 0.0000

Data Index: 1172657 (The Pile)

Max Activating Token Index: 407

Text #7

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.3416. Min Act: -0.0000

Data Index: 938943 (The Pile)

Max Activating Token Index: 595

Text #8

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.3222. Min Act: 0.0000

Data Index: 1245072 (The Pile)

Max Activating Token Index: 179

Text #9

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.3097. Min Act: -0.0000

Data Index: 1814216 (The Pile)

Max Activating Token Index: 984

Text #10

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.3082. Min Act: -0.0001

Data Index: 86258 (The Pile)

Max Activating Token Index: 355

Text #11

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.3177. Min Act: -0.0000

Data Index: 787046 (The Pile)

Max Activating Token Index: 270

Text #12

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.3138. Min Act: -0.0001

Data Index: 450084 (The Pile)

Max Activating Token Index: 167

Text #13

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.2928. Min Act: -0.0000

Data Index: 800437 (The Pile)

Max Activating Token Index: 15

Text #14

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.3095. Min Act: -0.0000

Data Index: 1089757 (The Pile)

Max Activating Token Index: 158

Text #15

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.3100. Min Act: 0.0000

Data Index: 1118861 (The Pile)

Max Activating Token Index: 411

Text #16

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.3047. Min Act: -0.0000

Data Index: 1249473 (The Pile)

Max Activating Token Index: 454

Text #17

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.3323. Min Act: -0.0001

Data Index: 1158787 (The Pile)

Max Activating Token Index: 871

Text #18

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.2942. Min Act: -0.0000

Data Index: 362089 (The Pile)

Max Activating Token Index: 722

Text #19

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.2904. Min Act: -0.0000

Data Index: 367075 (The Pile)

Max Activating Token Index: 866