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

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

Neuron 5390 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5049. Min Range: -3.5049

Max Act: 3.4004. Min Act: -0.0000

Data Index: 177899 (C4 (Web Text))

Max Activating Token Index: 680

Text #1

Max Range: 3.5049. Min Range: -3.5049

Max Act: 3.5049. Min Act: -0.0000

Data Index: 57441 (C4 (Web Text))

Max Activating Token Index: 141

Text #2

Max Range: 3.5049. Min Range: -3.5049

Max Act: 2.9457. Min Act: -0.0000

Data Index: 496403 (C4 (Web Text))

Max Activating Token Index: 322

Text #3

Max Range: 3.5049. Min Range: -3.5049

Max Act: 2.8382. Min Act: -0.0000

Data Index: 103276 (C4 (Web Text))

Max Activating Token Index: 94

Text #4

Max Range: 3.5049. Min Range: -3.5049

Max Act: 2.5818. Min Act: -0.0000

Data Index: 583641 (C4 (Web Text))

Max Activating Token Index: 366

Text #5

Max Range: 3.5049. Min Range: -3.5049

Max Act: 2.7969. Min Act: -0.0000

Data Index: 375877 (C4 (Web Text))

Max Activating Token Index: 543

Text #6

Max Range: 3.5049. Min Range: -3.5049

Max Act: 2.6521. Min Act: -0.0000

Data Index: 1002703 (C4 (Web Text))

Max Activating Token Index: 392

Text #7

Max Range: 3.5049. Min Range: -3.5049

Max Act: 2.8304. Min Act: -0.0000

Data Index: 276693 (C4 (Web Text))

Max Activating Token Index: 990

Text #8

Max Range: 3.5049. Min Range: -3.5049

Max Act: 2.6884. Min Act: -0.0000

Data Index: 1161572 (C4 (Web Text))

Max Activating Token Index: 81

Text #9

Max Range: 3.5049. Min Range: -3.5049

Max Act: 2.5346. Min Act: -0.0000

Data Index: 1037845 (C4 (Web Text))

Max Activating Token Index: 31

Text #10

Max Range: 3.5049. Min Range: -3.5049

Max Act: 2.6257. Min Act: -0.0000

Data Index: 52580 (C4 (Web Text))

Max Activating Token Index: 104

Text #11

Max Range: 3.5049. Min Range: -3.5049

Max Act: 2.4565. Min Act: -0.0000

Data Index: 340367 (C4 (Web Text))

Max Activating Token Index: 98

Text #12

Max Range: 3.5049. Min Range: -3.5049

Max Act: 2.5681. Min Act: -0.0000

Data Index: 418273 (C4 (Web Text))

Max Activating Token Index: 59

Text #13

Max Range: 3.5049. Min Range: -3.5049

Max Act: 2.7076. Min Act: -0.0000

Data Index: 879787 (C4 (Web Text))

Max Activating Token Index: 215

Text #14

Max Range: 3.5049. Min Range: -3.5049

Max Act: 2.6815. Min Act: -0.0000

Data Index: 1106774 (C4 (Web Text))

Max Activating Token Index: 751

Text #15

Max Range: 3.5049. Min Range: -3.5049

Max Act: 2.3021. Min Act: -0.0000

Data Index: 406529 (C4 (Web Text))

Max Activating Token Index: 212

Text #16

Max Range: 3.5049. Min Range: -3.5049

Max Act: 2.6764. Min Act: -0.0000

Data Index: 972174 (C4 (Web Text))

Max Activating Token Index: 72

Text #17

Max Range: 3.5049. Min Range: -3.5049

Max Act: 2.5314. Min Act: -0.0000

Data Index: 22231 (C4 (Web Text))

Max Activating Token Index: 97

Text #18

Max Range: 3.5049. Min Range: -3.5049

Max Act: 2.3929. Min Act: -0.0000

Data Index: 903659 (C4 (Web Text))

Max Activating Token Index: 515

Text #19

Max Range: 3.5049. Min Range: -3.5049

Max Act: 2.5213. Min Act: -0.0000

Data Index: 1135215 (C4 (Web Text))

Max Activating Token Index: 555