Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1547 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0099. Min Act: -0.0001

Data Index: 964797 (C4 (Web Text))

Max Activating Token Index: 568

Text #1

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0085. Min Act: -0.0001

Data Index: 1638286 (Python Code)

Max Activating Token Index: 46

Text #2

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0081. Min Act: -0.0001

Data Index: 1593604 (Python Code)

Max Activating Token Index: 986

Text #3

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0073. Min Act: -0.0001

Data Index: 1423355 (Python Code)

Max Activating Token Index: 829

Text #4

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0074. Min Act: -0.0001

Data Index: 1523914 (Python Code)

Max Activating Token Index: 467

Text #5

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0072. Min Act: -0.0001

Data Index: 1235975 (C4 (Web Text))

Max Activating Token Index: 467

Text #6

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0071. Min Act: -0.0001

Data Index: 1638646 (Python Code)

Max Activating Token Index: 418

Text #7

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0075. Min Act: -0.0001

Data Index: 757856 (C4 (Web Text))

Max Activating Token Index: 465

Text #8

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0069. Min Act: -0.0001

Data Index: 885827 (C4 (Web Text))

Max Activating Token Index: 934

Text #9

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0070. Min Act: -0.0001

Data Index: 1563077 (Python Code)

Max Activating Token Index: 972

Text #10

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0071. Min Act: -0.0001

Data Index: 465406 (C4 (Web Text))

Max Activating Token Index: 395

Text #11

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0064. Min Act: -0.0001

Data Index: 1423334 (Python Code)

Max Activating Token Index: 686

Text #12

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0067. Min Act: -0.0001

Data Index: 1639882 (Python Code)

Max Activating Token Index: 793

Text #13

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0067. Min Act: -0.0001

Data Index: 1083124 (C4 (Web Text))

Max Activating Token Index: 715

Text #14

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0066. Min Act: -0.0001

Data Index: 1596333 (Python Code)

Max Activating Token Index: 588

Text #15

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0068. Min Act: -0.0001

Data Index: 1598984 (Python Code)

Max Activating Token Index: 508

Text #16

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0066. Min Act: -0.0001

Data Index: 1574311 (Python Code)

Max Activating Token Index: 166

Text #17

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0067. Min Act: -0.0001

Data Index: 1579754 (Python Code)

Max Activating Token Index: 90

Text #18

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0065. Min Act: -0.0001

Data Index: 1366788 (Python Code)

Max Activating Token Index: 894

Text #19

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0065. Min Act: -0.0001

Data Index: 1428000 (Python Code)

Max Activating Token Index: 769