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

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

Neuron 241 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: 3.8046. Min Range: -3.8046

Max Act: 3.8046. Min Act: -0.0000

Data Index: 339967 (C4 (Web Text))

Max Activating Token Index: 335

Text #1

Max Range: 3.8046. Min Range: -3.8046

Max Act: 3.6552. Min Act: -0.0000

Data Index: 771296 (C4 (Web Text))

Max Activating Token Index: 900

Text #2

Max Range: 3.8046. Min Range: -3.8046

Max Act: 3.7997. Min Act: -0.0000

Data Index: 6648 (C4 (Web Text))

Max Activating Token Index: 597

Text #3

Max Range: 3.8046. Min Range: -3.8046

Max Act: 3.2693. Min Act: -0.0000

Data Index: 87667 (C4 (Web Text))

Max Activating Token Index: 623

Text #4

Max Range: 3.8046. Min Range: -3.8046

Max Act: 3.4237. Min Act: -0.0000

Data Index: 1300743 (C4 (Web Text))

Max Activating Token Index: 670

Text #5

Max Range: 3.8046. Min Range: -3.8046

Max Act: 3.3598. Min Act: -0.0000

Data Index: 450852 (C4 (Web Text))

Max Activating Token Index: 364

Text #6

Max Range: 3.8046. Min Range: -3.8046

Max Act: 3.5042. Min Act: -0.0000

Data Index: 924992 (C4 (Web Text))

Max Activating Token Index: 391

Text #7

Max Range: 3.8046. Min Range: -3.8046

Max Act: 3.3226. Min Act: -0.0000

Data Index: 938486 (C4 (Web Text))

Max Activating Token Index: 222

Text #8

Max Range: 3.8046. Min Range: -3.8046

Max Act: 2.9243. Min Act: -0.0000

Data Index: 321141 (C4 (Web Text))

Max Activating Token Index: 209

Text #9

Max Range: 3.8046. Min Range: -3.8046

Max Act: 2.6540. Min Act: -0.0000

Data Index: 932352 (C4 (Web Text))

Max Activating Token Index: 134

Text #10

Max Range: 3.8046. Min Range: -3.8046

Max Act: 2.4384. Min Act: -0.0000

Data Index: 1626465 (Python Code)

Max Activating Token Index: 925

Text #11

Max Range: 3.8046. Min Range: -3.8046

Max Act: 2.3923. Min Act: -0.0000

Data Index: 592267 (C4 (Web Text))

Max Activating Token Index: 194

Text #12

Max Range: 3.8046. Min Range: -3.8046

Max Act: 2.3776. Min Act: -0.0000

Data Index: 531157 (C4 (Web Text))

Max Activating Token Index: 150

Text #13

Max Range: 3.8046. Min Range: -3.8046

Max Act: 2.2498. Min Act: -0.0000

Data Index: 908374 (C4 (Web Text))

Max Activating Token Index: 677

Text #14

Max Range: 3.8046. Min Range: -3.8046

Max Act: 1.8765. Min Act: -0.0000

Data Index: 1518954 (Python Code)

Max Activating Token Index: 492

Text #15

Max Range: 3.8046. Min Range: -3.8046

Max Act: 2.0439. Min Act: -0.0000

Data Index: 306309 (C4 (Web Text))

Max Activating Token Index: 117

Text #16

Max Range: 3.8046. Min Range: -3.8046

Max Act: 2.0328. Min Act: -0.0000

Data Index: 664513 (C4 (Web Text))

Max Activating Token Index: 98

Text #17

Max Range: 3.8046. Min Range: -3.8046

Max Act: 1.8969. Min Act: -0.0000

Data Index: 1403064 (Python Code)

Max Activating Token Index: 1005

Text #18

Max Range: 3.8046. Min Range: -3.8046

Max Act: 1.9781. Min Act: -0.0000

Data Index: 825562 (C4 (Web Text))

Max Activating Token Index: 360

Text #19

Max Range: 3.8046. Min Range: -3.8046

Max Act: 1.9571. Min Act: -0.0000

Data Index: 1587407 (Python Code)

Max Activating Token Index: 97