Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2070 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0101. Min Act: -0.0004

Data Index: 1320239 (C4 (Web Text))

Max Activating Token Index: 837

Text #1

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0098. Min Act: -0.0004

Data Index: 527776 (C4 (Web Text))

Max Activating Token Index: 502

Text #2

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0095. Min Act: -0.0003

Data Index: 400768 (C4 (Web Text))

Max Activating Token Index: 544

Text #3

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0087. Min Act: -0.0004

Data Index: 802341 (C4 (Web Text))

Max Activating Token Index: 267

Text #4

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0089. Min Act: -0.0004

Data Index: 29007 (C4 (Web Text))

Max Activating Token Index: 276

Text #5

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0090. Min Act: -0.0004

Data Index: 253388 (C4 (Web Text))

Max Activating Token Index: 494

Text #6

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0088. Min Act: -0.0004

Data Index: 1048384 (C4 (Web Text))

Max Activating Token Index: 332

Text #7

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0085. Min Act: -0.0004

Data Index: 1068774 (C4 (Web Text))

Max Activating Token Index: 698

Text #8

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0084. Min Act: -0.0004

Data Index: 1354056 (C4 (Web Text))

Max Activating Token Index: 538

Text #9

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0084. Min Act: -0.0003

Data Index: 1209530 (C4 (Web Text))

Max Activating Token Index: 641

Text #10

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0080. Min Act: -0.0004

Data Index: 697652 (C4 (Web Text))

Max Activating Token Index: 544

Text #11

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0082. Min Act: -0.0004

Data Index: 171745 (C4 (Web Text))

Max Activating Token Index: 411

Text #12

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0081. Min Act: -0.0004

Data Index: 436325 (C4 (Web Text))

Max Activating Token Index: 625

Text #13

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0083. Min Act: -0.0004

Data Index: 1012730 (C4 (Web Text))

Max Activating Token Index: 425

Text #14

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0079. Min Act: -0.0003

Data Index: 954075 (C4 (Web Text))

Max Activating Token Index: 850

Text #15

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0077. Min Act: -0.0004

Data Index: 400578 (C4 (Web Text))

Max Activating Token Index: 89

Text #16

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0075. Min Act: -0.0004

Data Index: 1017701 (C4 (Web Text))

Max Activating Token Index: 459

Text #17

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0076. Min Act: -0.0003

Data Index: 502018 (C4 (Web Text))

Max Activating Token Index: 631

Text #18

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0077. Min Act: -0.0004

Data Index: 182873 (C4 (Web Text))

Max Activating Token Index: 585

Text #19

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0075. Min Act: -0.0003

Data Index: 808372 (C4 (Web Text))

Max Activating Token Index: 839