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

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

Neuron 670 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.9704. Min Range: -0.9704

Max Act: 0.9704. Min Act: -0.0001

Data Index: 555328 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 0.9704. Min Range: -0.9704

Max Act: 0.9400. Min Act: -0.0001

Data Index: 391561 (C4 (Web Text))

Max Activating Token Index: 6

Text #2

Max Range: 0.9704. Min Range: -0.9704

Max Act: 0.8915. Min Act: -0.0001

Data Index: 522781 (C4 (Web Text))

Max Activating Token Index: 91

Text #3

Max Range: 0.9704. Min Range: -0.9704

Max Act: 0.8831. Min Act: -0.0001

Data Index: 173344 (C4 (Web Text))

Max Activating Token Index: 57

Text #4

Max Range: 0.9704. Min Range: -0.9704

Max Act: 0.8759. Min Act: -0.0001

Data Index: 525953 (C4 (Web Text))

Max Activating Token Index: 45

Text #5

Max Range: 0.9704. Min Range: -0.9704

Max Act: 0.8610. Min Act: -0.0001

Data Index: 578345 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 0.9704. Min Range: -0.9704

Max Act: 0.8540. Min Act: -0.0001

Data Index: 801020 (C4 (Web Text))

Max Activating Token Index: 85

Text #7

Max Range: 0.9704. Min Range: -0.9704

Max Act: 0.8688. Min Act: -0.0001

Data Index: 644971 (C4 (Web Text))

Max Activating Token Index: 53

Text #8

Max Range: 0.9704. Min Range: -0.9704

Max Act: 0.8382. Min Act: -0.0001

Data Index: 909274 (C4 (Web Text))

Max Activating Token Index: 66

Text #9

Max Range: 0.9704. Min Range: -0.9704

Max Act: 0.8450. Min Act: -0.0001

Data Index: 1085315 (C4 (Web Text))

Max Activating Token Index: 3

Text #10

Max Range: 0.9704. Min Range: -0.9704

Max Act: 0.8389. Min Act: -0.0001

Data Index: 1160804 (C4 (Web Text))

Max Activating Token Index: 105

Text #11

Max Range: 0.9704. Min Range: -0.9704

Max Act: 0.8249. Min Act: -0.0001

Data Index: 569891 (C4 (Web Text))

Max Activating Token Index: 231

Text #12

Max Range: 0.9704. Min Range: -0.9704

Max Act: 0.8084. Min Act: -0.0001

Data Index: 819114 (C4 (Web Text))

Max Activating Token Index: 18

Text #13

Max Range: 0.9704. Min Range: -0.9704

Max Act: 0.8215. Min Act: -0.0001

Data Index: 1019086 (C4 (Web Text))

Max Activating Token Index: 61

Text #14

Max Range: 0.9704. Min Range: -0.9704

Max Act: 0.7984. Min Act: -0.0001

Data Index: 453624 (C4 (Web Text))

Max Activating Token Index: 736

Text #15

Max Range: 0.9704. Min Range: -0.9704

Max Act: 0.7928. Min Act: -0.0001

Data Index: 772447 (C4 (Web Text))

Max Activating Token Index: 48

Text #16

Max Range: 0.9704. Min Range: -0.9704

Max Act: 0.7884. Min Act: -0.0001

Data Index: 766988 (C4 (Web Text))

Max Activating Token Index: 59

Text #17

Max Range: 0.9704. Min Range: -0.9704

Max Act: 0.7802. Min Act: -0.0001

Data Index: 953368 (C4 (Web Text))

Max Activating Token Index: 125

Text #18

Max Range: 0.9704. Min Range: -0.9704

Max Act: 0.7917. Min Act: -0.0001

Data Index: 143494 (C4 (Web Text))

Max Activating Token Index: 29

Text #19

Max Range: 0.9704. Min Range: -0.9704

Max Act: 0.7841. Min Act: -0.0001

Data Index: 439209 (C4 (Web Text))

Max Activating Token Index: 891