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

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

Neuron 672 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: 0.5469. Min Range: -0.5469

Max Act: 0.5469. Min Act: -0.0001

Data Index: 584001 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 0.5469. Min Range: -0.5469

Max Act: 0.5341. Min Act: -0.0001

Data Index: 26869 (C4 (Web Text))

Max Activating Token Index: 4

Text #2

Max Range: 0.5469. Min Range: -0.5469

Max Act: 0.5347. Min Act: -0.0001

Data Index: 410034 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 0.5469. Min Range: -0.5469

Max Act: 0.5228. Min Act: -0.0001

Data Index: 1343111 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 0.5469. Min Range: -0.5469

Max Act: 0.5208. Min Act: -0.0001

Data Index: 230801 (C4 (Web Text))

Max Activating Token Index: 305

Text #5

Max Range: 0.5469. Min Range: -0.5469

Max Act: 0.5139. Min Act: -0.0001

Data Index: 410844 (C4 (Web Text))

Max Activating Token Index: 8

Text #6

Max Range: 0.5469. Min Range: -0.5469

Max Act: 0.5207. Min Act: -0.0001

Data Index: 786827 (C4 (Web Text))

Max Activating Token Index: 9

Text #7

Max Range: 0.5469. Min Range: -0.5469

Max Act: 0.5034. Min Act: -0.0001

Data Index: 1101474 (C4 (Web Text))

Max Activating Token Index: 514

Text #8

Max Range: 0.5469. Min Range: -0.5469

Max Act: 0.4964. Min Act: -0.0001

Data Index: 1081015 (C4 (Web Text))

Max Activating Token Index: 4

Text #9

Max Range: 0.5469. Min Range: -0.5469

Max Act: 0.4964. Min Act: -0.0001

Data Index: 1061292 (C4 (Web Text))

Max Activating Token Index: 4

Text #10

Max Range: 0.5469. Min Range: -0.5469

Max Act: 0.4964. Min Act: -0.0001

Data Index: 137395 (C4 (Web Text))

Max Activating Token Index: 4

Text #11

Max Range: 0.5469. Min Range: -0.5469

Max Act: 0.4878. Min Act: -0.0001

Data Index: 1135356 (C4 (Web Text))

Max Activating Token Index: 194

Text #12

Max Range: 0.5469. Min Range: -0.5469

Max Act: 0.4895. Min Act: -0.0001

Data Index: 26810 (C4 (Web Text))

Max Activating Token Index: 5

Text #13

Max Range: 0.5469. Min Range: -0.5469

Max Act: 0.5017. Min Act: -0.0001

Data Index: 303034 (C4 (Web Text))

Max Activating Token Index: 13

Text #14

Max Range: 0.5469. Min Range: -0.5469

Max Act: 0.4975. Min Act: -0.0001

Data Index: 1304905 (C4 (Web Text))

Max Activating Token Index: 5

Text #15

Max Range: 0.5469. Min Range: -0.5469

Max Act: 0.4902. Min Act: -0.0001

Data Index: 1110288 (C4 (Web Text))

Max Activating Token Index: 652

Text #16

Max Range: 0.5469. Min Range: -0.5469

Max Act: 0.4862. Min Act: -0.0001

Data Index: 353615 (C4 (Web Text))

Max Activating Token Index: 5

Text #17

Max Range: 0.5469. Min Range: -0.5469

Max Act: 0.4879. Min Act: -0.0001

Data Index: 291945 (C4 (Web Text))

Max Activating Token Index: 778

Text #18

Max Range: 0.5469. Min Range: -0.5469

Max Act: 0.4877. Min Act: -0.0001

Data Index: 460898 (C4 (Web Text))

Max Activating Token Index: 7

Text #19

Max Range: 0.5469. Min Range: -0.5469

Max Act: 0.4917. Min Act: -0.0001

Data Index: 646249 (C4 (Web Text))

Max Activating Token Index: 3