Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 731 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4805. Min Range: -0.4805

Max Act: 0.4683. Min Act: -0.0001

Data Index: 322026 (C4 (Web Text))

Max Activating Token Index: 518

Text #1

Max Range: 0.4805. Min Range: -0.4805

Max Act: 0.4487. Min Act: -0.0001

Data Index: 662642 (C4 (Web Text))

Max Activating Token Index: 1000

Text #2

Max Range: 0.4805. Min Range: -0.4805

Max Act: 0.4524. Min Act: -0.0001

Data Index: 6608 (C4 (Web Text))

Max Activating Token Index: 467

Text #3

Max Range: 0.4805. Min Range: -0.4805

Max Act: 0.4092. Min Act: -0.0001

Data Index: 892824 (C4 (Web Text))

Max Activating Token Index: 653

Text #4

Max Range: 0.4805. Min Range: -0.4805

Max Act: 0.4452. Min Act: -0.0001

Data Index: 186169 (C4 (Web Text))

Max Activating Token Index: 381

Text #5

Max Range: 0.4805. Min Range: -0.4805

Max Act: 0.4244. Min Act: -0.0001

Data Index: 147441 (C4 (Web Text))

Max Activating Token Index: 570

Text #6

Max Range: 0.4805. Min Range: -0.4805

Max Act: 0.4396. Min Act: -0.0001

Data Index: 1145990 (C4 (Web Text))

Max Activating Token Index: 411

Text #7

Max Range: 0.4805. Min Range: -0.4805

Max Act: 0.4805. Min Act: -0.0001

Data Index: 989195 (C4 (Web Text))

Max Activating Token Index: 198

Text #8

Max Range: 0.4805. Min Range: -0.4805

Max Act: 0.4007. Min Act: -0.0001

Data Index: 792771 (C4 (Web Text))

Max Activating Token Index: 205

Text #9

Max Range: 0.4805. Min Range: -0.4805

Max Act: 0.4412. Min Act: -0.0001

Data Index: 340023 (C4 (Web Text))

Max Activating Token Index: 300

Text #10

Max Range: 0.4805. Min Range: -0.4805

Max Act: 0.4424. Min Act: -0.0001

Data Index: 320799 (C4 (Web Text))

Max Activating Token Index: 601

Text #11

Max Range: 0.4805. Min Range: -0.4805

Max Act: 0.4154. Min Act: -0.0001

Data Index: 412363 (C4 (Web Text))

Max Activating Token Index: 760

Text #12

Max Range: 0.4805. Min Range: -0.4805

Max Act: 0.3893. Min Act: -0.0001

Data Index: 40011 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 0.4805. Min Range: -0.4805

Max Act: 0.4163. Min Act: -0.0001

Data Index: 460206 (C4 (Web Text))

Max Activating Token Index: 337

Text #14

Max Range: 0.4805. Min Range: -0.4805

Max Act: 0.3905. Min Act: -0.0001

Data Index: 462318 (C4 (Web Text))

Max Activating Token Index: 846

Text #15

Max Range: 0.4805. Min Range: -0.4805

Max Act: 0.3709. Min Act: -0.0001

Data Index: 1226018 (C4 (Web Text))

Max Activating Token Index: 643

Text #16

Max Range: 0.4805. Min Range: -0.4805

Max Act: 0.3905. Min Act: -0.0001

Data Index: 777313 (C4 (Web Text))

Max Activating Token Index: 934

Text #17

Max Range: 0.4805. Min Range: -0.4805

Max Act: 0.3817. Min Act: -0.0001

Data Index: 1121195 (C4 (Web Text))

Max Activating Token Index: 193

Text #18

Max Range: 0.4805. Min Range: -0.4805

Max Act: 0.3811. Min Act: -0.0001

Data Index: 609090 (C4 (Web Text))

Max Activating Token Index: 892

Text #19

Max Range: 0.4805. Min Range: -0.4805

Max Act: 0.3927. Min Act: -0.0001

Data Index: 461676 (C4 (Web Text))

Max Activating Token Index: 589