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

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

Neuron 630 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: 0.5233. Min Range: -0.5233

Max Act: 0.5206. Min Act: -0.0001

Data Index: 74010 (C4 (Web Text))

Max Activating Token Index: 223

Text #1

Max Range: 0.5233. Min Range: -0.5233

Max Act: 0.5233. Min Act: -0.0001

Data Index: 648083 (C4 (Web Text))

Max Activating Token Index: 793

Text #2

Max Range: 0.5233. Min Range: -0.5233

Max Act: 0.5148. Min Act: -0.0001

Data Index: 1032030 (C4 (Web Text))

Max Activating Token Index: 552

Text #3

Max Range: 0.5233. Min Range: -0.5233

Max Act: 0.5117. Min Act: -0.0002

Data Index: 1052072 (C4 (Web Text))

Max Activating Token Index: 238

Text #4

Max Range: 0.5233. Min Range: -0.5233

Max Act: 0.5066. Min Act: -0.0001

Data Index: 276072 (C4 (Web Text))

Max Activating Token Index: 17

Text #5

Max Range: 0.5233. Min Range: -0.5233

Max Act: 0.5079. Min Act: -0.0001

Data Index: 274622 (C4 (Web Text))

Max Activating Token Index: 413

Text #6

Max Range: 0.5233. Min Range: -0.5233

Max Act: 0.5117. Min Act: -0.0001

Data Index: 134734 (C4 (Web Text))

Max Activating Token Index: 391

Text #7

Max Range: 0.5233. Min Range: -0.5233

Max Act: 0.4870. Min Act: -0.0001

Data Index: 493680 (C4 (Web Text))

Max Activating Token Index: 528

Text #8

Max Range: 0.5233. Min Range: -0.5233

Max Act: 0.4992. Min Act: -0.0001

Data Index: 1262973 (C4 (Web Text))

Max Activating Token Index: 148

Text #9

Max Range: 0.5233. Min Range: -0.5233

Max Act: 0.5025. Min Act: -0.0001

Data Index: 1049500 (C4 (Web Text))

Max Activating Token Index: 999

Text #10

Max Range: 0.5233. Min Range: -0.5233

Max Act: 0.4942. Min Act: -0.0001

Data Index: 843921 (C4 (Web Text))

Max Activating Token Index: 609

Text #11

Max Range: 0.5233. Min Range: -0.5233

Max Act: 0.4845. Min Act: -0.0001

Data Index: 377758 (C4 (Web Text))

Max Activating Token Index: 882

Text #12

Max Range: 0.5233. Min Range: -0.5233

Max Act: 0.4884. Min Act: -0.0001

Data Index: 479530 (C4 (Web Text))

Max Activating Token Index: 97

Text #13

Max Range: 0.5233. Min Range: -0.5233

Max Act: 0.4836. Min Act: -0.0001

Data Index: 352229 (C4 (Web Text))

Max Activating Token Index: 965

Text #14

Max Range: 0.5233. Min Range: -0.5233

Max Act: 0.4921. Min Act: -0.0001

Data Index: 301606 (C4 (Web Text))

Max Activating Token Index: 135

Text #15

Max Range: 0.5233. Min Range: -0.5233

Max Act: 0.4863. Min Act: -0.0001

Data Index: 566335 (C4 (Web Text))

Max Activating Token Index: 283

Text #16

Max Range: 0.5233. Min Range: -0.5233

Max Act: 0.4799. Min Act: -0.0001

Data Index: 541226 (C4 (Web Text))

Max Activating Token Index: 464

Text #17

Max Range: 0.5233. Min Range: -0.5233

Max Act: 0.4916. Min Act: -0.0001

Data Index: 211305 (C4 (Web Text))

Max Activating Token Index: 97

Text #18

Max Range: 0.5233. Min Range: -0.5233

Max Act: 0.4965. Min Act: -0.0002

Data Index: 694587 (C4 (Web Text))

Max Activating Token Index: 854

Text #19

Max Range: 0.5233. Min Range: -0.5233

Max Act: 0.4850. Min Act: -0.0001

Data Index: 32608 (C4 (Web Text))

Max Activating Token Index: 826