Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1510 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0067. Min Act: -0.0006

Data Index: 1460069 (Python Code)

Max Activating Token Index: 1005

Text #1

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0047. Min Act: -0.0006

Data Index: 1535947 (Python Code)

Max Activating Token Index: 448

Text #2

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0058. Min Act: -0.0006

Data Index: 1617057 (Python Code)

Max Activating Token Index: 759

Text #3

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0054. Min Act: -0.0006

Data Index: 1372352 (Python Code)

Max Activating Token Index: 539

Text #4

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0053. Min Act: -0.0006

Data Index: 769388 (C4 (Web Text))

Max Activating Token Index: 977

Text #5

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0061. Min Act: -0.0006

Data Index: 1540135 (Python Code)

Max Activating Token Index: 347

Text #6

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0059. Min Act: -0.0006

Data Index: 1458308 (Python Code)

Max Activating Token Index: 339

Text #7

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0057. Min Act: -0.0006

Data Index: 1625797 (Python Code)

Max Activating Token Index: 602

Text #8

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0057. Min Act: -0.0006

Data Index: 634810 (C4 (Web Text))

Max Activating Token Index: 65

Text #9

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0051. Min Act: -0.0006

Data Index: 1535408 (Python Code)

Max Activating Token Index: 437

Text #10

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0054. Min Act: -0.0006

Data Index: 964633 (C4 (Web Text))

Max Activating Token Index: 213

Text #11

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0055. Min Act: -0.0006

Data Index: 520054 (C4 (Web Text))

Max Activating Token Index: 131

Text #12

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0053. Min Act: -0.0006

Data Index: 1582179 (Python Code)

Max Activating Token Index: 749

Text #13

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0048. Min Act: -0.0006

Data Index: 775694 (C4 (Web Text))

Max Activating Token Index: 889

Text #14

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0052. Min Act: -0.0006

Data Index: 625077 (C4 (Web Text))

Max Activating Token Index: 377

Text #15

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0061. Min Act: -0.0006

Data Index: 1565056 (Python Code)

Max Activating Token Index: 473

Text #16

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0050. Min Act: -0.0006

Data Index: 1473234 (Python Code)

Max Activating Token Index: 180

Text #17

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0050. Min Act: -0.0006

Data Index: 1231430 (C4 (Web Text))

Max Activating Token Index: 308

Text #18

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0049. Min Act: -0.0006

Data Index: 1507916 (Python Code)

Max Activating Token Index: 252

Text #19

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0051. Min Act: -0.0006

Data Index: 1476853 (Python Code)

Max Activating Token Index: 326