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

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

Neuron 1638 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0088. Min Act: -0.0003

Data Index: 1553747 (Python Code)

Max Activating Token Index: 802

Text #1

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0083. Min Act: -0.0003

Data Index: 1434758 (Python Code)

Max Activating Token Index: 225

Text #2

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0083. Min Act: -0.0003

Data Index: 1570904 (Python Code)

Max Activating Token Index: 239

Text #3

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0078. Min Act: -0.0003

Data Index: 118522 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0078. Min Act: -0.0003

Data Index: 1416474 (Python Code)

Max Activating Token Index: 651

Text #5

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0079. Min Act: -0.0004

Data Index: 515702 (C4 (Web Text))

Max Activating Token Index: 962

Text #6

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0078. Min Act: -0.0003

Data Index: 1536629 (Python Code)

Max Activating Token Index: 245

Text #7

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0077. Min Act: -0.0003

Data Index: 1420747 (Python Code)

Max Activating Token Index: 137

Text #8

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0075. Min Act: -0.0003

Data Index: 865230 (C4 (Web Text))

Max Activating Token Index: 860

Text #9

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0075. Min Act: -0.0003

Data Index: 1617118 (Python Code)

Max Activating Token Index: 246

Text #10

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0075. Min Act: -0.0003

Data Index: 1117848 (C4 (Web Text))

Max Activating Token Index: 618

Text #11

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0074. Min Act: -0.0003

Data Index: 1434621 (Python Code)

Max Activating Token Index: 771

Text #12

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0073. Min Act: -0.0003

Data Index: 566127 (C4 (Web Text))

Max Activating Token Index: 807

Text #13

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0073. Min Act: -0.0004

Data Index: 40785 (C4 (Web Text))

Max Activating Token Index: 695

Text #14

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0073. Min Act: -0.0003

Data Index: 1383728 (Python Code)

Max Activating Token Index: 124

Text #15

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0073. Min Act: -0.0003

Data Index: 1420310 (Python Code)

Max Activating Token Index: 581

Text #16

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0072. Min Act: -0.0003

Data Index: 1576992 (Python Code)

Max Activating Token Index: 803

Text #17

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0072. Min Act: -0.0003

Data Index: 1453954 (Python Code)

Max Activating Token Index: 385

Text #18

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0072. Min Act: -0.0003

Data Index: 1613452 (Python Code)

Max Activating Token Index: 454

Text #19

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0072. Min Act: -0.0003

Data Index: 1643076 (Python Code)

Max Activating Token Index: 253