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

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

Neuron 2215 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: 0.0058. Min Range: -0.0058

Max Act: 0.0058. Min Act: -0.0003

Data Index: 1435320 (Python Code)

Max Activating Token Index: 10

Text #1

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0055. Min Act: -0.0003

Data Index: 296666 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0054. Min Act: -0.0003

Data Index: 1482025 (Python Code)

Max Activating Token Index: 153

Text #3

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0054. Min Act: -0.0003

Data Index: 1632256 (Python Code)

Max Activating Token Index: 278

Text #4

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0052. Min Act: -0.0003

Data Index: 1360045 (Python Code)

Max Activating Token Index: 653

Text #5

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0051. Min Act: -0.0003

Data Index: 211209 (C4 (Web Text))

Max Activating Token Index: 774

Text #6

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0051. Min Act: -0.0003

Data Index: 1586967 (Python Code)

Max Activating Token Index: 788

Text #7

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0051. Min Act: -0.0003

Data Index: 1616194 (Python Code)

Max Activating Token Index: 856

Text #8

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0051. Min Act: -0.0003

Data Index: 1394987 (Python Code)

Max Activating Token Index: 8

Text #9

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0051. Min Act: -0.0003

Data Index: 1599460 (Python Code)

Max Activating Token Index: 85

Text #10

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0050. Min Act: -0.0003

Data Index: 1641546 (Python Code)

Max Activating Token Index: 710

Text #11

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0050. Min Act: -0.0003

Data Index: 1514572 (Python Code)

Max Activating Token Index: 576

Text #12

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0049. Min Act: -0.0003

Data Index: 1507935 (Python Code)

Max Activating Token Index: 103

Text #13

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0050. Min Act: -0.0003

Data Index: 566788 (C4 (Web Text))

Max Activating Token Index: 440

Text #14

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0049. Min Act: -0.0003

Data Index: 1652337 (Python Code)

Max Activating Token Index: 375

Text #15

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0049. Min Act: -0.0003

Data Index: 1585806 (Python Code)

Max Activating Token Index: 36

Text #16

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0048. Min Act: -0.0004

Data Index: 1389938 (Python Code)

Max Activating Token Index: 942

Text #17

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0048. Min Act: -0.0003

Data Index: 1647024 (Python Code)

Max Activating Token Index: 6

Text #18

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0048. Min Act: -0.0003

Data Index: 1564518 (Python Code)

Max Activating Token Index: 312

Text #19

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0049. Min Act: -0.0003

Data Index: 1638555 (Python Code)

Max Activating Token Index: 381