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

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

Neuron 647 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0101. Min Act: -0.0002

Data Index: 949407 (C4 (Web Text))

Max Activating Token Index: 238

Text #1

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0090. Min Act: -0.0002

Data Index: 1235266 (C4 (Web Text))

Max Activating Token Index: 170

Text #2

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0088. Min Act: -0.0002

Data Index: 541367 (C4 (Web Text))

Max Activating Token Index: 544

Text #3

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0089. Min Act: -0.0002

Data Index: 1201786 (C4 (Web Text))

Max Activating Token Index: 437

Text #4

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0088. Min Act: -0.0002

Data Index: 258099 (C4 (Web Text))

Max Activating Token Index: 542

Text #5

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0088. Min Act: -0.0002

Data Index: 948720 (C4 (Web Text))

Max Activating Token Index: 79

Text #6

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0085. Min Act: -0.0002

Data Index: 278433 (C4 (Web Text))

Max Activating Token Index: 694

Text #7

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0087. Min Act: -0.0002

Data Index: 1035287 (C4 (Web Text))

Max Activating Token Index: 865

Text #8

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0086. Min Act: -0.0002

Data Index: 588877 (C4 (Web Text))

Max Activating Token Index: 621

Text #9

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0084. Min Act: -0.0002

Data Index: 584727 (C4 (Web Text))

Max Activating Token Index: 610

Text #10

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0085. Min Act: -0.0002

Data Index: 951024 (C4 (Web Text))

Max Activating Token Index: 247

Text #11

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0083. Min Act: -0.0002

Data Index: 341079 (C4 (Web Text))

Max Activating Token Index: 810

Text #12

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0085. Min Act: -0.0002

Data Index: 396855 (C4 (Web Text))

Max Activating Token Index: 596

Text #13

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0084. Min Act: -0.0002

Data Index: 1349779 (C4 (Web Text))

Max Activating Token Index: 642

Text #14

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0084. Min Act: -0.0002

Data Index: 788767 (C4 (Web Text))

Max Activating Token Index: 711

Text #15

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0083. Min Act: -0.0002

Data Index: 929940 (C4 (Web Text))

Max Activating Token Index: 726

Text #16

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0083. Min Act: -0.0002

Data Index: 875948 (C4 (Web Text))

Max Activating Token Index: 207

Text #17

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0083. Min Act: -0.0002

Data Index: 686986 (C4 (Web Text))

Max Activating Token Index: 280

Text #18

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0082. Min Act: -0.0002

Data Index: 216537 (C4 (Web Text))

Max Activating Token Index: 187

Text #19

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0082. Min Act: -0.0002

Data Index: 1116315 (C4 (Web Text))

Max Activating Token Index: 197