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

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

Neuron 3052 in Layer 1

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: 0.7139. Min Range: -0.7139

Max Act: 0.7119. Min Act: -0.0002

Data Index: 463528 (C4 (Web Text))

Max Activating Token Index: 95

Text #1

Max Range: 0.7139. Min Range: -0.7139

Max Act: 0.7139. Min Act: -0.0002

Data Index: 94202 (C4 (Web Text))

Max Activating Token Index: 733

Text #2

Max Range: 0.7139. Min Range: -0.7139

Max Act: 0.6730. Min Act: -0.0002

Data Index: 108201 (C4 (Web Text))

Max Activating Token Index: 15

Text #3

Max Range: 0.7139. Min Range: -0.7139

Max Act: 0.6460. Min Act: -0.0002

Data Index: 275394 (C4 (Web Text))

Max Activating Token Index: 37

Text #4

Max Range: 0.7139. Min Range: -0.7139

Max Act: 0.6406. Min Act: -0.0002

Data Index: 253059 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 0.7139. Min Range: -0.7139

Max Act: 0.6305. Min Act: -0.0002

Data Index: 513813 (C4 (Web Text))

Max Activating Token Index: 903

Text #6

Max Range: 0.7139. Min Range: -0.7139

Max Act: 0.6230. Min Act: -0.0002

Data Index: 62173 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 0.7139. Min Range: -0.7139

Max Act: 0.6388. Min Act: -0.0002

Data Index: 239665 (C4 (Web Text))

Max Activating Token Index: 68

Text #8

Max Range: 0.7139. Min Range: -0.7139

Max Act: 0.6182. Min Act: -0.0002

Data Index: 1212018 (C4 (Web Text))

Max Activating Token Index: 24

Text #9

Max Range: 0.7139. Min Range: -0.7139

Max Act: 0.6082. Min Act: -0.0002

Data Index: 23619 (C4 (Web Text))

Max Activating Token Index: 84

Text #10

Max Range: 0.7139. Min Range: -0.7139

Max Act: 0.6003. Min Act: -0.0002

Data Index: 436608 (C4 (Web Text))

Max Activating Token Index: 626

Text #11

Max Range: 0.7139. Min Range: -0.7139

Max Act: 0.6060. Min Act: -0.0002

Data Index: 340884 (C4 (Web Text))

Max Activating Token Index: 154

Text #12

Max Range: 0.7139. Min Range: -0.7139

Max Act: 0.6047. Min Act: -0.0002

Data Index: 1201357 (C4 (Web Text))

Max Activating Token Index: 745

Text #13

Max Range: 0.7139. Min Range: -0.7139

Max Act: 0.5861. Min Act: -0.0002

Data Index: 571794 (C4 (Web Text))

Max Activating Token Index: 165

Text #14

Max Range: 0.7139. Min Range: -0.7139

Max Act: 0.5900. Min Act: -0.0002

Data Index: 660331 (C4 (Web Text))

Max Activating Token Index: 527

Text #15

Max Range: 0.7139. Min Range: -0.7139

Max Act: 0.5865. Min Act: -0.0002

Data Index: 313630 (C4 (Web Text))

Max Activating Token Index: 27

Text #16

Max Range: 0.7139. Min Range: -0.7139

Max Act: 0.5904. Min Act: -0.0002

Data Index: 502975 (C4 (Web Text))

Max Activating Token Index: 133

Text #17

Max Range: 0.7139. Min Range: -0.7139

Max Act: 0.5874. Min Act: -0.0002

Data Index: 1336197 (C4 (Web Text))

Max Activating Token Index: 714

Text #18

Max Range: 0.7139. Min Range: -0.7139

Max Act: 0.5891. Min Act: -0.0002

Data Index: 1004839 (C4 (Web Text))

Max Activating Token Index: 112

Text #19

Max Range: 0.7139. Min Range: -0.7139

Max Act: 0.5833. Min Act: -0.0002

Data Index: 521500 (C4 (Web Text))

Max Activating Token Index: 63