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

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

Neuron 1927 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: 2.4683. Min Range: -2.4683

Max Act: 2.4457. Min Act: -0.0002

Data Index: 659154 (C4 (Web Text))

Max Activating Token Index: 647

Text #1

Max Range: 2.4683. Min Range: -2.4683

Max Act: 2.4607. Min Act: -0.0002

Data Index: 655898 (C4 (Web Text))

Max Activating Token Index: 30

Text #2

Max Range: 2.4683. Min Range: -2.4683

Max Act: 2.4683. Min Act: -0.0002

Data Index: 776239 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 2.4683. Min Range: -2.4683

Max Act: 2.4300. Min Act: -0.0002

Data Index: 33850 (C4 (Web Text))

Max Activating Token Index: 66

Text #4

Max Range: 2.4683. Min Range: -2.4683

Max Act: 2.3818. Min Act: -0.0002

Data Index: 61376 (C4 (Web Text))

Max Activating Token Index: 9

Text #5

Max Range: 2.4683. Min Range: -2.4683

Max Act: 2.3569. Min Act: -0.0002

Data Index: 1132170 (C4 (Web Text))

Max Activating Token Index: 330

Text #6

Max Range: 2.4683. Min Range: -2.4683

Max Act: 2.3164. Min Act: -0.0002

Data Index: 1053551 (C4 (Web Text))

Max Activating Token Index: 47

Text #7

Max Range: 2.4683. Min Range: -2.4683

Max Act: 2.3677. Min Act: -0.0002

Data Index: 309386 (C4 (Web Text))

Max Activating Token Index: 59

Text #8

Max Range: 2.4683. Min Range: -2.4683

Max Act: 2.2904. Min Act: -0.0002

Data Index: 305184 (C4 (Web Text))

Max Activating Token Index: 80

Text #9

Max Range: 2.4683. Min Range: -2.4683

Max Act: 2.2755. Min Act: -0.0002

Data Index: 1309962 (C4 (Web Text))

Max Activating Token Index: 224

Text #10

Max Range: 2.4683. Min Range: -2.4683

Max Act: 2.2552. Min Act: -0.0002

Data Index: 939793 (C4 (Web Text))

Max Activating Token Index: 824

Text #11

Max Range: 2.4683. Min Range: -2.4683

Max Act: 2.2225. Min Act: -0.0002

Data Index: 1285118 (C4 (Web Text))

Max Activating Token Index: 6

Text #12

Max Range: 2.4683. Min Range: -2.4683

Max Act: 2.2560. Min Act: -0.0002

Data Index: 1232883 (C4 (Web Text))

Max Activating Token Index: 22

Text #13

Max Range: 2.4683. Min Range: -2.4683

Max Act: 2.1585. Min Act: -0.0002

Data Index: 138190 (C4 (Web Text))

Max Activating Token Index: 25

Text #14

Max Range: 2.4683. Min Range: -2.4683

Max Act: 2.2960. Min Act: -0.0002

Data Index: 1283124 (C4 (Web Text))

Max Activating Token Index: 94

Text #15

Max Range: 2.4683. Min Range: -2.4683

Max Act: 2.2299. Min Act: -0.0002

Data Index: 1321890 (C4 (Web Text))

Max Activating Token Index: 228

Text #16

Max Range: 2.4683. Min Range: -2.4683

Max Act: 2.2299. Min Act: -0.0002

Data Index: 493525 (C4 (Web Text))

Max Activating Token Index: 17

Text #17

Max Range: 2.4683. Min Range: -2.4683

Max Act: 2.2668. Min Act: -0.0002

Data Index: 995482 (C4 (Web Text))

Max Activating Token Index: 195

Text #18

Max Range: 2.4683. Min Range: -2.4683

Max Act: 2.2036. Min Act: -0.0003

Data Index: 58684 (C4 (Web Text))

Max Activating Token Index: 147

Text #19

Max Range: 2.4683. Min Range: -2.4683

Max Act: 2.2293. Min Act: -0.0002

Data Index: 662071 (C4 (Web Text))

Max Activating Token Index: 330