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

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

Neuron 3587 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.8916. Min Act: -0.0000

Data Index: 153058 (C4 (Web Text))

Max Activating Token Index: 561

Text #1

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.6934. Min Act: -0.0000

Data Index: 148138 (C4 (Web Text))

Max Activating Token Index: 974

Text #2

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.7103. Min Act: -0.0000

Data Index: 695633 (C4 (Web Text))

Max Activating Token Index: 316

Text #3

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.7081. Min Act: -0.0000

Data Index: 201931 (C4 (Web Text))

Max Activating Token Index: 373

Text #4

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.6768. Min Act: -0.0000

Data Index: 551261 (C4 (Web Text))

Max Activating Token Index: 293

Text #5

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.6265. Min Act: -0.0000

Data Index: 1027398 (C4 (Web Text))

Max Activating Token Index: 630

Text #6

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.6666. Min Act: -0.0000

Data Index: 343281 (C4 (Web Text))

Max Activating Token Index: 113

Text #7

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.6668. Min Act: -0.0000

Data Index: 659293 (C4 (Web Text))

Max Activating Token Index: 913

Text #8

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.6179. Min Act: -0.0000

Data Index: 238743 (C4 (Web Text))

Max Activating Token Index: 645

Text #9

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.6334. Min Act: -0.0000

Data Index: 418993 (C4 (Web Text))

Max Activating Token Index: 448

Text #10

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.6562. Min Act: -0.0000

Data Index: 564645 (C4 (Web Text))

Max Activating Token Index: 98

Text #11

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.6078. Min Act: -0.0000

Data Index: 658501 (C4 (Web Text))

Max Activating Token Index: 654

Text #12

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.6250. Min Act: -0.0000

Data Index: 1318846 (C4 (Web Text))

Max Activating Token Index: 890

Text #13

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.6047. Min Act: -0.0000

Data Index: 563738 (C4 (Web Text))

Max Activating Token Index: 69

Text #14

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.6036. Min Act: -0.0000

Data Index: 20157 (C4 (Web Text))

Max Activating Token Index: 550

Text #15

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.5525. Min Act: -0.0000

Data Index: 88192 (C4 (Web Text))

Max Activating Token Index: 293

Text #16

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.5955. Min Act: -0.0000

Data Index: 316381 (C4 (Web Text))

Max Activating Token Index: 332

Text #17

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.5695. Min Act: -0.0000

Data Index: 266405 (C4 (Web Text))

Max Activating Token Index: 230

Text #18

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.6247. Min Act: -0.0000

Data Index: 671254 (C4 (Web Text))

Max Activating Token Index: 820

Text #19

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.5683. Min Act: -0.0000

Data Index: 713845 (C4 (Web Text))

Max Activating Token Index: 215