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

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

Neuron 4012 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: 0.3775. Min Range: -0.3775

Max Act: 0.3775. Min Act: -0.0001

Data Index: 1602692 (Python Code)

Max Activating Token Index: 553

Text #1

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.3560. Min Act: -0.0001

Data Index: 1535699 (Python Code)

Max Activating Token Index: 602

Text #2

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.3271. Min Act: -0.0001

Data Index: 1423440 (Python Code)

Max Activating Token Index: 278

Text #3

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.3448. Min Act: -0.0001

Data Index: 1451687 (Python Code)

Max Activating Token Index: 999

Text #4

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.3239. Min Act: -0.0001

Data Index: 1520848 (Python Code)

Max Activating Token Index: 30

Text #5

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.3053. Min Act: -0.0001

Data Index: 1515071 (Python Code)

Max Activating Token Index: 271

Text #6

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.3122. Min Act: -0.0001

Data Index: 1474939 (Python Code)

Max Activating Token Index: 263

Text #7

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.3096. Min Act: -0.0001

Data Index: 1466280 (Python Code)

Max Activating Token Index: 174

Text #8

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.3118. Min Act: -0.0001

Data Index: 1512722 (Python Code)

Max Activating Token Index: 760

Text #9

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.3108. Min Act: -0.0001

Data Index: 1389646 (Python Code)

Max Activating Token Index: 41

Text #10

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.3084. Min Act: -0.0001

Data Index: 1575766 (Python Code)

Max Activating Token Index: 144

Text #11

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.3082. Min Act: -0.0001

Data Index: 1477987 (Python Code)

Max Activating Token Index: 958

Text #12

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.3058. Min Act: -0.0001

Data Index: 1415426 (Python Code)

Max Activating Token Index: 69

Text #13

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.3074. Min Act: -0.0001

Data Index: 1392319 (Python Code)

Max Activating Token Index: 915

Text #14

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.3253. Min Act: -0.0001

Data Index: 1612367 (Python Code)

Max Activating Token Index: 935

Text #15

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.3136. Min Act: -0.0001

Data Index: 1482034 (Python Code)

Max Activating Token Index: 104

Text #16

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.2929. Min Act: -0.0001

Data Index: 1563734 (Python Code)

Max Activating Token Index: 194

Text #17

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.2931. Min Act: -0.0001

Data Index: 1377585 (Python Code)

Max Activating Token Index: 35

Text #18

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.2921. Min Act: -0.0001

Data Index: 1520519 (Python Code)

Max Activating Token Index: 381

Text #19

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.3016. Min Act: -0.0001

Data Index: 1400484 (Python Code)

Max Activating Token Index: 73