Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1637 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0101. Min Act: -0.0003

Data Index: 158894 (C4 (Web Text))

Max Activating Token Index: 409

Text #1

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0090. Min Act: -0.0003

Data Index: 534870 (C4 (Web Text))

Max Activating Token Index: 178

Text #2

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0089. Min Act: -0.0003

Data Index: 841008 (C4 (Web Text))

Max Activating Token Index: 252

Text #3

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0088. Min Act: -0.0003

Data Index: 141891 (C4 (Web Text))

Max Activating Token Index: 76

Text #4

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0087. Min Act: -0.0003

Data Index: 956146 (C4 (Web Text))

Max Activating Token Index: 790

Text #5

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0086. Min Act: -0.0003

Data Index: 401347 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0085. Min Act: -0.0003

Data Index: 1003420 (C4 (Web Text))

Max Activating Token Index: 572

Text #7

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0084. Min Act: -0.0003

Data Index: 527859 (C4 (Web Text))

Max Activating Token Index: 255

Text #8

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0084. Min Act: -0.0003

Data Index: 914677 (C4 (Web Text))

Max Activating Token Index: 34

Text #9

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0081. Min Act: -0.0003

Data Index: 272681 (C4 (Web Text))

Max Activating Token Index: 437

Text #10

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0081. Min Act: -0.0003

Data Index: 793062 (C4 (Web Text))

Max Activating Token Index: 294

Text #11

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0079. Min Act: -0.0003

Data Index: 834297 (C4 (Web Text))

Max Activating Token Index: 332

Text #12

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0080. Min Act: -0.0003

Data Index: 701937 (C4 (Web Text))

Max Activating Token Index: 14

Text #13

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0080. Min Act: -0.0003

Data Index: 956762 (C4 (Web Text))

Max Activating Token Index: 280

Text #14

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0080. Min Act: -0.0003

Data Index: 310634 (C4 (Web Text))

Max Activating Token Index: 117

Text #15

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0080. Min Act: -0.0003

Data Index: 164514 (C4 (Web Text))

Max Activating Token Index: 50

Text #16

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0080. Min Act: -0.0002

Data Index: 1402383 (Python Code)

Max Activating Token Index: 219

Text #17

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0079. Min Act: -0.0003

Data Index: 782276 (C4 (Web Text))

Max Activating Token Index: 12

Text #18

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0078. Min Act: -0.0003

Data Index: 522006 (C4 (Web Text))

Max Activating Token Index: 381

Text #19

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0078. Min Act: -0.0002

Data Index: 1314365 (C4 (Web Text))

Max Activating Token Index: 170