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

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

Neuron 2887 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0129. Min Act: -0.0004

Data Index: 386909 (C4 (Web Text))

Max Activating Token Index: 122

Text #1

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0113. Min Act: -0.0004

Data Index: 1249876 (C4 (Web Text))

Max Activating Token Index: 230

Text #2

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0104. Min Act: -0.0004

Data Index: 101463 (C4 (Web Text))

Max Activating Token Index: 435

Text #3

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0094. Min Act: -0.0004

Data Index: 837313 (C4 (Web Text))

Max Activating Token Index: 330

Text #4

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0094. Min Act: -0.0004

Data Index: 499328 (C4 (Web Text))

Max Activating Token Index: 698

Text #5

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0089. Min Act: -0.0004

Data Index: 659098 (C4 (Web Text))

Max Activating Token Index: 264

Text #6

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0095. Min Act: -0.0004

Data Index: 305548 (C4 (Web Text))

Max Activating Token Index: 829

Text #7

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0093. Min Act: -0.0004

Data Index: 806596 (C4 (Web Text))

Max Activating Token Index: 778

Text #8

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0088. Min Act: -0.0004

Data Index: 1010814 (C4 (Web Text))

Max Activating Token Index: 501

Text #9

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0094. Min Act: -0.0004

Data Index: 964702 (C4 (Web Text))

Max Activating Token Index: 238

Text #10

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0096. Min Act: -0.0004

Data Index: 364133 (C4 (Web Text))

Max Activating Token Index: 509

Text #11

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0070. Min Act: -0.0004

Data Index: 986966 (C4 (Web Text))

Max Activating Token Index: 557

Text #12

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0078. Min Act: -0.0004

Data Index: 44796 (C4 (Web Text))

Max Activating Token Index: 344

Text #13

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0092. Min Act: -0.0004

Data Index: 1049760 (C4 (Web Text))

Max Activating Token Index: 536

Text #14

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0079. Min Act: -0.0004

Data Index: 771796 (C4 (Web Text))

Max Activating Token Index: 343

Text #15

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0085. Min Act: -0.0004

Data Index: 437026 (C4 (Web Text))

Max Activating Token Index: 389

Text #16

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0094. Min Act: -0.0004

Data Index: 316694 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0087. Min Act: -0.0004

Data Index: 1291295 (C4 (Web Text))

Max Activating Token Index: 434

Text #18

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0091. Min Act: -0.0004

Data Index: 506754 (C4 (Web Text))

Max Activating Token Index: 483

Text #19

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0095. Min Act: -0.0004

Data Index: 694677 (C4 (Web Text))

Max Activating Token Index: 373