Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4063 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0070. Min Act: -0.0003

Data Index: 225503 (C4 (Web Text))

Max Activating Token Index: 218

Text #1

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0057. Min Act: -0.0003

Data Index: 183860 (C4 (Web Text))

Max Activating Token Index: 872

Text #2

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0058. Min Act: -0.0003

Data Index: 55790 (C4 (Web Text))

Max Activating Token Index: 562

Text #3

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0051. Min Act: -0.0003

Data Index: 1120234 (C4 (Web Text))

Max Activating Token Index: 652

Text #4

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0051. Min Act: -0.0003

Data Index: 1349992 (C4 (Web Text))

Max Activating Token Index: 620

Text #5

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0053. Min Act: -0.0003

Data Index: 514820 (C4 (Web Text))

Max Activating Token Index: 278

Text #6

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0053. Min Act: -0.0004

Data Index: 29375 (C4 (Web Text))

Max Activating Token Index: 567

Text #7

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0048. Min Act: -0.0003

Data Index: 712466 (C4 (Web Text))

Max Activating Token Index: 994

Text #8

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0049. Min Act: -0.0003

Data Index: 510479 (C4 (Web Text))

Max Activating Token Index: 790

Text #9

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0050. Min Act: -0.0003

Data Index: 1388461 (Python Code)

Max Activating Token Index: 948

Text #10

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0049. Min Act: -0.0003

Data Index: 476033 (C4 (Web Text))

Max Activating Token Index: 129

Text #11

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0050. Min Act: -0.0003

Data Index: 1308189 (C4 (Web Text))

Max Activating Token Index: 644

Text #12

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0049. Min Act: -0.0003

Data Index: 1624762 (Python Code)

Max Activating Token Index: 972

Text #13

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0051. Min Act: -0.0003

Data Index: 435257 (C4 (Web Text))

Max Activating Token Index: 751

Text #14

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0046. Min Act: -0.0003

Data Index: 1630465 (Python Code)

Max Activating Token Index: 1005

Text #15

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0045. Min Act: -0.0003

Data Index: 1253857 (C4 (Web Text))

Max Activating Token Index: 870

Text #16

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0048. Min Act: -0.0003

Data Index: 838699 (C4 (Web Text))

Max Activating Token Index: 452

Text #17

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0045. Min Act: -0.0003

Data Index: 695112 (C4 (Web Text))

Max Activating Token Index: 329

Text #18

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0049. Min Act: -0.0003

Data Index: 739927 (C4 (Web Text))

Max Activating Token Index: 885

Text #19

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0046. Min Act: -0.0003

Data Index: 1148662 (C4 (Web Text))

Max Activating Token Index: 478