Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3689 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.2781. Min Range: -4.2781

Max Act: 4.1964. Min Act: -0.0000

Data Index: 930595 (C4 (Web Text))

Max Activating Token Index: 203

Text #1

Max Range: 4.2781. Min Range: -4.2781

Max Act: 4.2781. Min Act: -0.0000

Data Index: 301066 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 4.2781. Min Range: -4.2781

Max Act: 3.7525. Min Act: -0.0000

Data Index: 547987 (C4 (Web Text))

Max Activating Token Index: 321

Text #3

Max Range: 4.2781. Min Range: -4.2781

Max Act: 3.8836. Min Act: -0.0001

Data Index: 722161 (C4 (Web Text))

Max Activating Token Index: 951

Text #4

Max Range: 4.2781. Min Range: -4.2781

Max Act: 4.0065. Min Act: -0.0000

Data Index: 841289 (C4 (Web Text))

Max Activating Token Index: 614

Text #5

Max Range: 4.2781. Min Range: -4.2781

Max Act: 3.9043. Min Act: -0.0001

Data Index: 54400 (C4 (Web Text))

Max Activating Token Index: 202

Text #6

Max Range: 4.2781. Min Range: -4.2781

Max Act: 4.1131. Min Act: -0.0001

Data Index: 305132 (C4 (Web Text))

Max Activating Token Index: 799

Text #7

Max Range: 4.2781. Min Range: -4.2781

Max Act: 3.6167. Min Act: -0.0001

Data Index: 1052137 (C4 (Web Text))

Max Activating Token Index: 632

Text #8

Max Range: 4.2781. Min Range: -4.2781

Max Act: 3.5183. Min Act: -0.0000

Data Index: 514626 (C4 (Web Text))

Max Activating Token Index: 47

Text #9

Max Range: 4.2781. Min Range: -4.2781

Max Act: 3.4670. Min Act: -0.0000

Data Index: 597958 (C4 (Web Text))

Max Activating Token Index: 672

Text #10

Max Range: 4.2781. Min Range: -4.2781

Max Act: 3.7523. Min Act: -0.0000

Data Index: 706898 (C4 (Web Text))

Max Activating Token Index: 72

Text #11

Max Range: 4.2781. Min Range: -4.2781

Max Act: 3.5697. Min Act: -0.0000

Data Index: 244620 (C4 (Web Text))

Max Activating Token Index: 811

Text #12

Max Range: 4.2781. Min Range: -4.2781

Max Act: 3.3935. Min Act: -0.0000

Data Index: 925700 (C4 (Web Text))

Max Activating Token Index: 608

Text #13

Max Range: 4.2781. Min Range: -4.2781

Max Act: 3.3249. Min Act: -0.0000

Data Index: 876281 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 4.2781. Min Range: -4.2781

Max Act: 3.4885. Min Act: -0.0000

Data Index: 135870 (C4 (Web Text))

Max Activating Token Index: 165

Text #15

Max Range: 4.2781. Min Range: -4.2781

Max Act: 3.6436. Min Act: -0.0000

Data Index: 840962 (C4 (Web Text))

Max Activating Token Index: 452

Text #16

Max Range: 4.2781. Min Range: -4.2781

Max Act: 3.4885. Min Act: -0.0001

Data Index: 430093 (C4 (Web Text))

Max Activating Token Index: 577

Text #17

Max Range: 4.2781. Min Range: -4.2781

Max Act: 3.7831. Min Act: -0.0000

Data Index: 946242 (C4 (Web Text))

Max Activating Token Index: 1016

Text #18

Max Range: 4.2781. Min Range: -4.2781

Max Act: 3.3128. Min Act: -0.0001

Data Index: 286871 (C4 (Web Text))

Max Activating Token Index: 912

Text #19

Max Range: 4.2781. Min Range: -4.2781

Max Act: 3.3978. Min Act: -0.0000

Data Index: 132602 (C4 (Web Text))

Max Activating Token Index: 28