Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1643 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0129. Min Act: -0.0003

Data Index: 1043446 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0133. Min Act: -0.0003

Data Index: 1374439 (Python Code)

Max Activating Token Index: 74

Text #2

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0114. Min Act: -0.0003

Data Index: 350600 (C4 (Web Text))

Max Activating Token Index: 97

Text #3

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0115. Min Act: -0.0003

Data Index: 1306356 (C4 (Web Text))

Max Activating Token Index: 31

Text #4

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0107. Min Act: -0.0003

Data Index: 415594 (C4 (Web Text))

Max Activating Token Index: 554

Text #5

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0112. Min Act: -0.0003

Data Index: 131658 (C4 (Web Text))

Max Activating Token Index: 775

Text #6

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0110. Min Act: -0.0003

Data Index: 68339 (C4 (Web Text))

Max Activating Token Index: 154

Text #7

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0108. Min Act: -0.0003

Data Index: 1312535 (C4 (Web Text))

Max Activating Token Index: 513

Text #8

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0104. Min Act: -0.0003

Data Index: 76158 (C4 (Web Text))

Max Activating Token Index: 424

Text #9

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0098. Min Act: -0.0003

Data Index: 847954 (C4 (Web Text))

Max Activating Token Index: 112

Text #10

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0108. Min Act: -0.0003

Data Index: 66102 (C4 (Web Text))

Max Activating Token Index: 581

Text #11

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0103. Min Act: -0.0003

Data Index: 585438 (C4 (Web Text))

Max Activating Token Index: 112

Text #12

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0107. Min Act: -0.0003

Data Index: 1151042 (C4 (Web Text))

Max Activating Token Index: 77

Text #13

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0100. Min Act: -0.0003

Data Index: 1188500 (C4 (Web Text))

Max Activating Token Index: 50

Text #14

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0104. Min Act: -0.0003

Data Index: 1488302 (Python Code)

Max Activating Token Index: 690

Text #15

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0100. Min Act: -0.0003

Data Index: 642563 (C4 (Web Text))

Max Activating Token Index: 525

Text #16

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0095. Min Act: -0.0003

Data Index: 223309 (C4 (Web Text))

Max Activating Token Index: 123

Text #17

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0099. Min Act: -0.0003

Data Index: 438053 (C4 (Web Text))

Max Activating Token Index: 289

Text #18

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0095. Min Act: -0.0003

Data Index: 350898 (C4 (Web Text))

Max Activating Token Index: 54

Text #19

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0108. Min Act: -0.0003

Data Index: 1329035 (C4 (Web Text))

Max Activating Token Index: 838