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

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

Neuron 2833 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: 2.3112. Min Range: -2.3112

Max Act: 2.3030. Min Act: -0.0000

Data Index: 49576 (C4 (Web Text))

Max Activating Token Index: 121

Text #1

Max Range: 2.3112. Min Range: -2.3112

Max Act: 2.3112. Min Act: -0.0000

Data Index: 361767 (C4 (Web Text))

Max Activating Token Index: 500

Text #2

Max Range: 2.3112. Min Range: -2.3112

Max Act: 1.9444. Min Act: -0.0000

Data Index: 689261 (C4 (Web Text))

Max Activating Token Index: 514

Text #3

Max Range: 2.3112. Min Range: -2.3112

Max Act: 1.9052. Min Act: -0.0000

Data Index: 543466 (C4 (Web Text))

Max Activating Token Index: 303

Text #4

Max Range: 2.3112. Min Range: -2.3112

Max Act: 2.0067. Min Act: -0.0000

Data Index: 884517 (C4 (Web Text))

Max Activating Token Index: 62

Text #5

Max Range: 2.3112. Min Range: -2.3112

Max Act: 1.8040. Min Act: -0.0000

Data Index: 962815 (C4 (Web Text))

Max Activating Token Index: 732

Text #6

Max Range: 2.3112. Min Range: -2.3112

Max Act: 1.8559. Min Act: -0.0000

Data Index: 251997 (C4 (Web Text))

Max Activating Token Index: 55

Text #7

Max Range: 2.3112. Min Range: -2.3112

Max Act: 1.7627. Min Act: -0.0000

Data Index: 370609 (C4 (Web Text))

Max Activating Token Index: 202

Text #8

Max Range: 2.3112. Min Range: -2.3112

Max Act: 1.7613. Min Act: -0.0000

Data Index: 1337934 (C4 (Web Text))

Max Activating Token Index: 332

Text #9

Max Range: 2.3112. Min Range: -2.3112

Max Act: 1.7532. Min Act: -0.0000

Data Index: 1252910 (C4 (Web Text))

Max Activating Token Index: 548

Text #10

Max Range: 2.3112. Min Range: -2.3112

Max Act: 1.7371. Min Act: -0.0000

Data Index: 1104914 (C4 (Web Text))

Max Activating Token Index: 175

Text #11

Max Range: 2.3112. Min Range: -2.3112

Max Act: 1.6850. Min Act: -0.0000

Data Index: 121528 (C4 (Web Text))

Max Activating Token Index: 61

Text #12

Max Range: 2.3112. Min Range: -2.3112

Max Act: 1.6423. Min Act: -0.0000

Data Index: 892673 (C4 (Web Text))

Max Activating Token Index: 488

Text #13

Max Range: 2.3112. Min Range: -2.3112

Max Act: 1.6075. Min Act: -0.0000

Data Index: 86680 (C4 (Web Text))

Max Activating Token Index: 147

Text #14

Max Range: 2.3112. Min Range: -2.3112

Max Act: 1.7334. Min Act: -0.0000

Data Index: 884893 (C4 (Web Text))

Max Activating Token Index: 911

Text #15

Max Range: 2.3112. Min Range: -2.3112

Max Act: 1.5159. Min Act: -0.0000

Data Index: 587486 (C4 (Web Text))

Max Activating Token Index: 764

Text #16

Max Range: 2.3112. Min Range: -2.3112

Max Act: 1.5067. Min Act: -0.0000

Data Index: 711473 (C4 (Web Text))

Max Activating Token Index: 234

Text #17

Max Range: 2.3112. Min Range: -2.3112

Max Act: 1.5969. Min Act: -0.0000

Data Index: 1138364 (C4 (Web Text))

Max Activating Token Index: 873

Text #18

Max Range: 2.3112. Min Range: -2.3112

Max Act: 1.5806. Min Act: -0.0000

Data Index: 95591 (C4 (Web Text))

Max Activating Token Index: 611

Text #19

Max Range: 2.3112. Min Range: -2.3112

Max Act: 1.5888. Min Act: -0.0000

Data Index: 577326 (C4 (Web Text))

Max Activating Token Index: 560