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

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

Neuron 1385 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0139. Min Act: -0.0000

Data Index: 885468 (C4 (Web Text))

Max Activating Token Index: 223

Text #1

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0140. Min Act: -0.0000

Data Index: 300954 (C4 (Web Text))

Max Activating Token Index: 976

Text #2

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0123. Min Act: -0.0000

Data Index: 1640006 (Python Code)

Max Activating Token Index: 149

Text #3

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0102. Min Act: -0.0000

Data Index: 193669 (C4 (Web Text))

Max Activating Token Index: 158

Text #4

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0106. Min Act: -0.0000

Data Index: 1545324 (Python Code)

Max Activating Token Index: 141

Text #5

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0108. Min Act: -0.0000

Data Index: 1315073 (C4 (Web Text))

Max Activating Token Index: 76

Text #6

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0092. Min Act: -0.0000

Data Index: 599612 (C4 (Web Text))

Max Activating Token Index: 1015

Text #7

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0091. Min Act: -0.0000

Data Index: 320836 (C4 (Web Text))

Max Activating Token Index: 974

Text #8

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0094. Min Act: -0.0000

Data Index: 34669 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0090. Min Act: -0.0000

Data Index: 193073 (C4 (Web Text))

Max Activating Token Index: 804

Text #10

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0082. Min Act: -0.0000

Data Index: 1242582 (C4 (Web Text))

Max Activating Token Index: 960

Text #11

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0099. Min Act: -0.0000

Data Index: 1617063 (Python Code)

Max Activating Token Index: 117

Text #12

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0088. Min Act: -0.0000

Data Index: 976838 (C4 (Web Text))

Max Activating Token Index: 870

Text #13

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0089. Min Act: -0.0000

Data Index: 1416692 (Python Code)

Max Activating Token Index: 907

Text #14

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0086. Min Act: -0.0000

Data Index: 1382562 (Python Code)

Max Activating Token Index: 505

Text #15

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0082. Min Act: -0.0000

Data Index: 1012172 (C4 (Web Text))

Max Activating Token Index: 391

Text #16

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0083. Min Act: -0.0000

Data Index: 1477013 (Python Code)

Max Activating Token Index: 999

Text #17

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0078. Min Act: -0.0000

Data Index: 1431605 (Python Code)

Max Activating Token Index: 875

Text #18

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0086. Min Act: -0.0000

Data Index: 1650736 (Python Code)

Max Activating Token Index: 1022

Text #19

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0084. Min Act: -0.0000

Data Index: 775066 (C4 (Web Text))

Max Activating Token Index: 809