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

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

Neuron 3317 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: 0.5780. Min Range: -0.5780

Max Act: 0.5741. Min Act: -0.0002

Data Index: 707801 (C4 (Web Text))

Max Activating Token Index: 480

Text #1

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.5780. Min Act: -0.0002

Data Index: 630551 (C4 (Web Text))

Max Activating Token Index: 502

Text #2

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.5400. Min Act: -0.0002

Data Index: 183414 (C4 (Web Text))

Max Activating Token Index: 539

Text #3

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.5185. Min Act: -0.0002

Data Index: 43106 (C4 (Web Text))

Max Activating Token Index: 364

Text #4

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.5254. Min Act: -0.0002

Data Index: 181973 (C4 (Web Text))

Max Activating Token Index: 466

Text #5

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.5213. Min Act: -0.0002

Data Index: 996543 (C4 (Web Text))

Max Activating Token Index: 589

Text #6

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.5061. Min Act: -0.0002

Data Index: 719645 (C4 (Web Text))

Max Activating Token Index: 454

Text #7

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.5162. Min Act: -0.0002

Data Index: 1120714 (C4 (Web Text))

Max Activating Token Index: 687

Text #8

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.5147. Min Act: -0.0002

Data Index: 1340617 (C4 (Web Text))

Max Activating Token Index: 501

Text #9

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.4999. Min Act: -0.0002

Data Index: 338843 (C4 (Web Text))

Max Activating Token Index: 882

Text #10

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.5155. Min Act: -0.0002

Data Index: 509355 (C4 (Web Text))

Max Activating Token Index: 7

Text #11

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.4925. Min Act: -0.0002

Data Index: 765585 (C4 (Web Text))

Max Activating Token Index: 487

Text #12

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.4953. Min Act: -0.0002

Data Index: 882269 (C4 (Web Text))

Max Activating Token Index: 729

Text #13

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.5077. Min Act: -0.0002

Data Index: 167885 (C4 (Web Text))

Max Activating Token Index: 811

Text #14

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.4937. Min Act: -0.0002

Data Index: 1057295 (C4 (Web Text))

Max Activating Token Index: 543

Text #15

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.5069. Min Act: -0.0002

Data Index: 873394 (C4 (Web Text))

Max Activating Token Index: 649

Text #16

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.5028. Min Act: -0.0002

Data Index: 938090 (C4 (Web Text))

Max Activating Token Index: 722

Text #17

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.5077. Min Act: -0.0002

Data Index: 353202 (C4 (Web Text))

Max Activating Token Index: 5

Text #18

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.5062. Min Act: -0.0002

Data Index: 483054 (C4 (Web Text))

Max Activating Token Index: 413

Text #19

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.4952. Min Act: -0.0002

Data Index: 1157192 (C4 (Web Text))

Max Activating Token Index: 350