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

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

Neuron 5615 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5577. Min Range: -5.5577

Max Act: 5.5577. Min Act: -0.0000

Data Index: 255274 (C4 (Web Text))

Max Activating Token Index: 994

Text #1

Max Range: 5.5577. Min Range: -5.5577

Max Act: 4.1963. Min Act: -0.0000

Data Index: 1170966 (C4 (Web Text))

Max Activating Token Index: 718

Text #2

Max Range: 5.5577. Min Range: -5.5577

Max Act: 3.9826. Min Act: -0.0000

Data Index: 692662 (C4 (Web Text))

Max Activating Token Index: 684

Text #3

Max Range: 5.5577. Min Range: -5.5577

Max Act: 4.2550. Min Act: -0.0000

Data Index: 432320 (C4 (Web Text))

Max Activating Token Index: 894

Text #4

Max Range: 5.5577. Min Range: -5.5577

Max Act: 3.3837. Min Act: -0.0000

Data Index: 788464 (C4 (Web Text))

Max Activating Token Index: 244

Text #5

Max Range: 5.5577. Min Range: -5.5577

Max Act: 3.8203. Min Act: -0.0000

Data Index: 142709 (C4 (Web Text))

Max Activating Token Index: 511

Text #6

Max Range: 5.5577. Min Range: -5.5577

Max Act: 3.2075. Min Act: -0.0000

Data Index: 88904 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 5.5577. Min Range: -5.5577

Max Act: 3.5229. Min Act: -0.0000

Data Index: 196580 (C4 (Web Text))

Max Activating Token Index: 166

Text #8

Max Range: 5.5577. Min Range: -5.5577

Max Act: 3.4663. Min Act: -0.0000

Data Index: 456615 (C4 (Web Text))

Max Activating Token Index: 523

Text #9

Max Range: 5.5577. Min Range: -5.5577

Max Act: 3.1682. Min Act: -0.0000

Data Index: 565201 (C4 (Web Text))

Max Activating Token Index: 530

Text #10

Max Range: 5.5577. Min Range: -5.5577

Max Act: 3.1166. Min Act: -0.0000

Data Index: 872859 (C4 (Web Text))

Max Activating Token Index: 955

Text #11

Max Range: 5.5577. Min Range: -5.5577

Max Act: 2.7838. Min Act: -0.0000

Data Index: 976810 (C4 (Web Text))

Max Activating Token Index: 718

Text #12

Max Range: 5.5577. Min Range: -5.5577

Max Act: 2.9753. Min Act: -0.0000

Data Index: 96545 (C4 (Web Text))

Max Activating Token Index: 810

Text #13

Max Range: 5.5577. Min Range: -5.5577

Max Act: 3.1130. Min Act: -0.0000

Data Index: 448076 (C4 (Web Text))

Max Activating Token Index: 522

Text #14

Max Range: 5.5577. Min Range: -5.5577

Max Act: 3.0907. Min Act: -0.0000

Data Index: 360591 (C4 (Web Text))

Max Activating Token Index: 544

Text #15

Max Range: 5.5577. Min Range: -5.5577

Max Act: 3.0567. Min Act: -0.0000

Data Index: 891073 (C4 (Web Text))

Max Activating Token Index: 748

Text #16

Max Range: 5.5577. Min Range: -5.5577

Max Act: 3.0217. Min Act: -0.0000

Data Index: 582175 (C4 (Web Text))

Max Activating Token Index: 100

Text #17

Max Range: 5.5577. Min Range: -5.5577

Max Act: 3.1244. Min Act: -0.0000

Data Index: 205028 (C4 (Web Text))

Max Activating Token Index: 948

Text #18

Max Range: 5.5577. Min Range: -5.5577

Max Act: 3.2579. Min Act: -0.0000

Data Index: 1082518 (C4 (Web Text))

Max Activating Token Index: 108

Text #19

Max Range: 5.5577. Min Range: -5.5577

Max Act: 2.9422. Min Act: -0.0000

Data Index: 343070 (C4 (Web Text))

Max Activating Token Index: 276