Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 281 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0088. Min Act: -0.0006

Data Index: 64669 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0072. Min Act: -0.0006

Data Index: 1479116 (Python Code)

Max Activating Token Index: 630

Text #2

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0069. Min Act: -0.0005

Data Index: 805327 (C4 (Web Text))

Max Activating Token Index: 477

Text #3

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0067. Min Act: -0.0006

Data Index: 1028919 (C4 (Web Text))

Max Activating Token Index: 671

Text #4

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0067. Min Act: -0.0006

Data Index: 401820 (C4 (Web Text))

Max Activating Token Index: 473

Text #5

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0067. Min Act: -0.0006

Data Index: 860949 (C4 (Web Text))

Max Activating Token Index: 409

Text #6

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0067. Min Act: -0.0006

Data Index: 1058607 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0068. Min Act: -0.0005

Data Index: 1597187 (Python Code)

Max Activating Token Index: 383

Text #8

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0066. Min Act: -0.0006

Data Index: 579705 (C4 (Web Text))

Max Activating Token Index: 337

Text #9

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0064. Min Act: -0.0006

Data Index: 1295183 (C4 (Web Text))

Max Activating Token Index: 825

Text #10

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0064. Min Act: -0.0006

Data Index: 1570762 (Python Code)

Max Activating Token Index: 690

Text #11

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0063. Min Act: -0.0006

Data Index: 228078 (C4 (Web Text))

Max Activating Token Index: 734

Text #12

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0061. Min Act: -0.0006

Data Index: 498936 (C4 (Web Text))

Max Activating Token Index: 114

Text #13

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0061. Min Act: -0.0006

Data Index: 1101461 (C4 (Web Text))

Max Activating Token Index: 337

Text #14

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0061. Min Act: -0.0005

Data Index: 179541 (C4 (Web Text))

Max Activating Token Index: 83

Text #15

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0060. Min Act: -0.0006

Data Index: 304923 (C4 (Web Text))

Max Activating Token Index: 983

Text #16

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0061. Min Act: -0.0006

Data Index: 611263 (C4 (Web Text))

Max Activating Token Index: 969

Text #17

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0060. Min Act: -0.0006

Data Index: 384393 (C4 (Web Text))

Max Activating Token Index: 200

Text #18

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0060. Min Act: -0.0006

Data Index: 656346 (C4 (Web Text))

Max Activating Token Index: 394

Text #19

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0060. Min Act: -0.0006

Data Index: 817521 (C4 (Web Text))

Max Activating Token Index: 833