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

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

Neuron 2185 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0058. Min Range: -4.0058

Max Act: 4.0058. Min Act: -0.0000

Data Index: 744577 (C4 (Web Text))

Max Activating Token Index: 836

Text #1

Max Range: 4.0058. Min Range: -4.0058

Max Act: 3.8650. Min Act: -0.0000

Data Index: 97088 (C4 (Web Text))

Max Activating Token Index: 403

Text #2

Max Range: 4.0058. Min Range: -4.0058

Max Act: 3.1318. Min Act: -0.0000

Data Index: 350009 (C4 (Web Text))

Max Activating Token Index: 973

Text #3

Max Range: 4.0058. Min Range: -4.0058

Max Act: 2.9064. Min Act: -0.0000

Data Index: 103902 (C4 (Web Text))

Max Activating Token Index: 128

Text #4

Max Range: 4.0058. Min Range: -4.0058

Max Act: 2.6809. Min Act: -0.0000

Data Index: 42768 (C4 (Web Text))

Max Activating Token Index: 181

Text #5

Max Range: 4.0058. Min Range: -4.0058

Max Act: 2.6638. Min Act: -0.0000

Data Index: 574196 (C4 (Web Text))

Max Activating Token Index: 181

Text #6

Max Range: 4.0058. Min Range: -4.0058

Max Act: 2.6944. Min Act: -0.0000

Data Index: 188917 (C4 (Web Text))

Max Activating Token Index: 231

Text #7

Max Range: 4.0058. Min Range: -4.0058

Max Act: 2.7529. Min Act: -0.0000

Data Index: 1019070 (C4 (Web Text))

Max Activating Token Index: 632

Text #8

Max Range: 4.0058. Min Range: -4.0058

Max Act: 2.4778. Min Act: -0.0000

Data Index: 969058 (C4 (Web Text))

Max Activating Token Index: 413

Text #9

Max Range: 4.0058. Min Range: -4.0058

Max Act: 2.5887. Min Act: -0.0000

Data Index: 36612 (C4 (Web Text))

Max Activating Token Index: 510

Text #10

Max Range: 4.0058. Min Range: -4.0058

Max Act: 2.4603. Min Act: -0.0000

Data Index: 256670 (C4 (Web Text))

Max Activating Token Index: 564

Text #11

Max Range: 4.0058. Min Range: -4.0058

Max Act: 2.5743. Min Act: -0.0000

Data Index: 1299608 (C4 (Web Text))

Max Activating Token Index: 325

Text #12

Max Range: 4.0058. Min Range: -4.0058

Max Act: 2.4966. Min Act: -0.0000

Data Index: 1338978 (C4 (Web Text))

Max Activating Token Index: 941

Text #13

Max Range: 4.0058. Min Range: -4.0058

Max Act: 2.4053. Min Act: -0.0000

Data Index: 1248791 (C4 (Web Text))

Max Activating Token Index: 83

Text #14

Max Range: 4.0058. Min Range: -4.0058

Max Act: 2.2793. Min Act: -0.0000

Data Index: 963484 (C4 (Web Text))

Max Activating Token Index: 144

Text #15

Max Range: 4.0058. Min Range: -4.0058

Max Act: 2.5033. Min Act: -0.0000

Data Index: 1015734 (C4 (Web Text))

Max Activating Token Index: 15

Text #16

Max Range: 4.0058. Min Range: -4.0058

Max Act: 2.3523. Min Act: -0.0000

Data Index: 786852 (C4 (Web Text))

Max Activating Token Index: 182

Text #17

Max Range: 4.0058. Min Range: -4.0058

Max Act: 2.4579. Min Act: -0.0000

Data Index: 54265 (C4 (Web Text))

Max Activating Token Index: 420

Text #18

Max Range: 4.0058. Min Range: -4.0058

Max Act: 2.4782. Min Act: -0.0000

Data Index: 1108353 (C4 (Web Text))

Max Activating Token Index: 263

Text #19

Max Range: 4.0058. Min Range: -4.0058

Max Act: 2.4654. Min Act: -0.0000

Data Index: 167138 (C4 (Web Text))

Max Activating Token Index: 47