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

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

Neuron 5131 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: 0.3473. Min Range: -0.3473

Max Act: 0.3473. Min Act: -0.0001

Data Index: 677883 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.3262. Min Act: -0.0001

Data Index: 84764 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.3226. Min Act: -0.0001

Data Index: 357588 (C4 (Web Text))

Max Activating Token Index: 41

Text #3

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.3115. Min Act: -0.0001

Data Index: 635616 (C4 (Web Text))

Max Activating Token Index: 144

Text #4

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.3090. Min Act: -0.0001

Data Index: 423602 (C4 (Web Text))

Max Activating Token Index: 45

Text #5

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.3155. Min Act: -0.0001

Data Index: 1088066 (C4 (Web Text))

Max Activating Token Index: 179

Text #6

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.3018. Min Act: -0.0001

Data Index: 1479919 (Python Code)

Max Activating Token Index: 133

Text #7

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.3046. Min Act: -0.0001

Data Index: 1268769 (C4 (Web Text))

Max Activating Token Index: 666

Text #8

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.2950. Min Act: -0.0001

Data Index: 57696 (C4 (Web Text))

Max Activating Token Index: 138

Text #9

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.2927. Min Act: -0.0001

Data Index: 12238 (C4 (Web Text))

Max Activating Token Index: 206

Text #10

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.2995. Min Act: -0.0002

Data Index: 946849 (C4 (Web Text))

Max Activating Token Index: 1015

Text #11

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.2921. Min Act: -0.0001

Data Index: 14553 (C4 (Web Text))

Max Activating Token Index: 48

Text #12

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.2955. Min Act: -0.0001

Data Index: 1120807 (C4 (Web Text))

Max Activating Token Index: 134

Text #13

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.2948. Min Act: -0.0001

Data Index: 575813 (C4 (Web Text))

Max Activating Token Index: 932

Text #14

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.2868. Min Act: -0.0001

Data Index: 1168645 (C4 (Web Text))

Max Activating Token Index: 138

Text #15

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.2904. Min Act: -0.0001

Data Index: 182057 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.2924. Min Act: -0.0001

Data Index: 86412 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.2841. Min Act: -0.0001

Data Index: 830904 (C4 (Web Text))

Max Activating Token Index: 753

Text #18

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.2868. Min Act: -0.0001

Data Index: 509016 (C4 (Web Text))

Max Activating Token Index: 756

Text #19

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.2807. Min Act: -0.0001

Data Index: 311644 (C4 (Web Text))

Max Activating Token Index: 349