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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3397 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.5127. Min Act: -0.0000

Data Index: 465577 (C4 (Web Text))

Max Activating Token Index: 79

Text #1

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.4611. Min Act: -0.0000

Data Index: 214021 (C4 (Web Text))

Max Activating Token Index: 610

Text #2

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.4374. Min Act: -0.0000

Data Index: 73913 (C4 (Web Text))

Max Activating Token Index: 113

Text #3

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.4321. Min Act: -0.0000

Data Index: 1256588 (C4 (Web Text))

Max Activating Token Index: 462

Text #4

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.4126. Min Act: -0.0000

Data Index: 69245 (C4 (Web Text))

Max Activating Token Index: 779

Text #5

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.4379. Min Act: -0.0000

Data Index: 1022384 (C4 (Web Text))

Max Activating Token Index: 601

Text #6

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.4196. Min Act: -0.0000

Data Index: 910981 (C4 (Web Text))

Max Activating Token Index: 712

Text #7

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.4407. Min Act: -0.0000

Data Index: 994720 (C4 (Web Text))

Max Activating Token Index: 601

Text #8

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.4134. Min Act: -0.0000

Data Index: 1140882 (C4 (Web Text))

Max Activating Token Index: 646

Text #9

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.4147. Min Act: -0.0000

Data Index: 247207 (C4 (Web Text))

Max Activating Token Index: 403

Text #10

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.4154. Min Act: -0.0000

Data Index: 1032172 (C4 (Web Text))

Max Activating Token Index: 518

Text #11

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.4149. Min Act: -0.0000

Data Index: 579680 (C4 (Web Text))

Max Activating Token Index: 451

Text #12

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.4103. Min Act: -0.0000

Data Index: 214375 (C4 (Web Text))

Max Activating Token Index: 281

Text #13

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.4083. Min Act: -0.0000

Data Index: 27436 (C4 (Web Text))

Max Activating Token Index: 264

Text #14

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.4028. Min Act: -0.0000

Data Index: 441513 (C4 (Web Text))

Max Activating Token Index: 712

Text #15

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.3916. Min Act: -0.0000

Data Index: 265283 (C4 (Web Text))

Max Activating Token Index: 114

Text #16

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.4127. Min Act: -0.0000

Data Index: 911134 (C4 (Web Text))

Max Activating Token Index: 911

Text #17

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.3861. Min Act: -0.0000

Data Index: 447656 (C4 (Web Text))

Max Activating Token Index: 211

Text #18

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.3935. Min Act: -0.0000

Data Index: 289185 (C4 (Web Text))

Max Activating Token Index: 274

Text #19

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.3983. Min Act: -0.0000

Data Index: 292282 (C4 (Web Text))

Max Activating Token Index: 84