Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1776 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0090. Min Act: -0.0006

Data Index: 1161890 (C4 (Web Text))

Max Activating Token Index: 712

Text #1

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0092. Min Act: -0.0006

Data Index: 281012 (C4 (Web Text))

Max Activating Token Index: 817

Text #2

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0087. Min Act: -0.0007

Data Index: 1078071 (C4 (Web Text))

Max Activating Token Index: 106

Text #3

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0086. Min Act: -0.0006

Data Index: 943523 (C4 (Web Text))

Max Activating Token Index: 541

Text #4

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0086. Min Act: -0.0006

Data Index: 1314139 (C4 (Web Text))

Max Activating Token Index: 186

Text #5

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0085. Min Act: -0.0006

Data Index: 258082 (C4 (Web Text))

Max Activating Token Index: 810

Text #6

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0083. Min Act: -0.0006

Data Index: 722634 (C4 (Web Text))

Max Activating Token Index: 87

Text #7

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0084. Min Act: -0.0006

Data Index: 967903 (C4 (Web Text))

Max Activating Token Index: 245

Text #8

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0084. Min Act: -0.0006

Data Index: 608856 (C4 (Web Text))

Max Activating Token Index: 269

Text #9

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0083. Min Act: -0.0006

Data Index: 731342 (C4 (Web Text))

Max Activating Token Index: 785

Text #10

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0083. Min Act: -0.0006

Data Index: 1224855 (C4 (Web Text))

Max Activating Token Index: 515

Text #11

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0082. Min Act: -0.0006

Data Index: 332312 (C4 (Web Text))

Max Activating Token Index: 653

Text #12

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0081. Min Act: -0.0006

Data Index: 191316 (C4 (Web Text))

Max Activating Token Index: 129

Text #13

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0081. Min Act: -0.0007

Data Index: 484331 (C4 (Web Text))

Max Activating Token Index: 208

Text #14

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0081. Min Act: -0.0006

Data Index: 898087 (C4 (Web Text))

Max Activating Token Index: 286

Text #15

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0081. Min Act: -0.0006

Data Index: 784880 (C4 (Web Text))

Max Activating Token Index: 463

Text #16

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0079. Min Act: -0.0006

Data Index: 510007 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0081. Min Act: -0.0006

Data Index: 1138283 (C4 (Web Text))

Max Activating Token Index: 658

Text #18

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0080. Min Act: -0.0006

Data Index: 1242800 (C4 (Web Text))

Max Activating Token Index: 703

Text #19

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0080. Min Act: -0.0006

Data Index: 1183170 (C4 (Web Text))

Max Activating Token Index: 671