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

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

Neuron 2256 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6027. Min Range: -0.6027

Max Act: 0.6027. Min Act: -0.0001

Data Index: 321581 (C4 (Web Text))

Max Activating Token Index: 381

Text #1

Max Range: 0.6027. Min Range: -0.6027

Max Act: 0.5815. Min Act: -0.0001

Data Index: 550218 (C4 (Web Text))

Max Activating Token Index: 540

Text #2

Max Range: 0.6027. Min Range: -0.6027

Max Act: 0.5218. Min Act: -0.0001

Data Index: 294556 (C4 (Web Text))

Max Activating Token Index: 801

Text #3

Max Range: 0.6027. Min Range: -0.6027

Max Act: 0.5079. Min Act: -0.0001

Data Index: 368424 (C4 (Web Text))

Max Activating Token Index: 560

Text #4

Max Range: 0.6027. Min Range: -0.6027

Max Act: 0.4395. Min Act: -0.0001

Data Index: 563865 (C4 (Web Text))

Max Activating Token Index: 551

Text #5

Max Range: 0.6027. Min Range: -0.6027

Max Act: 0.5300. Min Act: -0.0001

Data Index: 1222769 (C4 (Web Text))

Max Activating Token Index: 654

Text #6

Max Range: 0.6027. Min Range: -0.6027

Max Act: 0.4750. Min Act: -0.0001

Data Index: 57817 (C4 (Web Text))

Max Activating Token Index: 920

Text #7

Max Range: 0.6027. Min Range: -0.6027

Max Act: 0.4609. Min Act: -0.0001

Data Index: 499638 (C4 (Web Text))

Max Activating Token Index: 227

Text #8

Max Range: 0.6027. Min Range: -0.6027

Max Act: 0.4466. Min Act: -0.0001

Data Index: 1169205 (C4 (Web Text))

Max Activating Token Index: 324

Text #9

Max Range: 0.6027. Min Range: -0.6027

Max Act: 0.5061. Min Act: -0.0001

Data Index: 972756 (C4 (Web Text))

Max Activating Token Index: 337

Text #10

Max Range: 0.6027. Min Range: -0.6027

Max Act: 0.5083. Min Act: -0.0001

Data Index: 1229966 (C4 (Web Text))

Max Activating Token Index: 891

Text #11

Max Range: 0.6027. Min Range: -0.6027

Max Act: 0.5348. Min Act: -0.0001

Data Index: 1023513 (C4 (Web Text))

Max Activating Token Index: 994

Text #12

Max Range: 0.6027. Min Range: -0.6027

Max Act: 0.4639. Min Act: -0.0001

Data Index: 639984 (C4 (Web Text))

Max Activating Token Index: 802

Text #13

Max Range: 0.6027. Min Range: -0.6027

Max Act: 0.4184. Min Act: -0.0001

Data Index: 1108167 (C4 (Web Text))

Max Activating Token Index: 540

Text #14

Max Range: 0.6027. Min Range: -0.6027

Max Act: 0.4482. Min Act: -0.0001

Data Index: 1017526 (C4 (Web Text))

Max Activating Token Index: 18

Text #15

Max Range: 0.6027. Min Range: -0.6027

Max Act: 0.4240. Min Act: -0.0001

Data Index: 268208 (C4 (Web Text))

Max Activating Token Index: 316

Text #16

Max Range: 0.6027. Min Range: -0.6027

Max Act: 0.4101. Min Act: -0.0001

Data Index: 1259020 (C4 (Web Text))

Max Activating Token Index: 117

Text #17

Max Range: 0.6027. Min Range: -0.6027

Max Act: 0.3836. Min Act: -0.0001

Data Index: 590271 (C4 (Web Text))

Max Activating Token Index: 123

Text #18

Max Range: 0.6027. Min Range: -0.6027

Max Act: 0.4326. Min Act: -0.0001

Data Index: 1025555 (C4 (Web Text))

Max Activating Token Index: 506

Text #19

Max Range: 0.6027. Min Range: -0.6027

Max Act: 0.4077. Min Act: -0.0001

Data Index: 1305324 (C4 (Web Text))

Max Activating Token Index: 206