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

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

Neuron 1827 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0112. Min Range: -0.0112

Max Act: 0.0112. Min Act: -0.0006

Data Index: 874779 (C4 (Web Text))

Max Activating Token Index: 989

Text #1

Max Range: 0.0112. Min Range: -0.0112

Max Act: 0.0098. Min Act: -0.0006

Data Index: 1215461 (C4 (Web Text))

Max Activating Token Index: 926

Text #2

Max Range: 0.0112. Min Range: -0.0112

Max Act: 0.0093. Min Act: -0.0006

Data Index: 525053 (C4 (Web Text))

Max Activating Token Index: 976

Text #3

Max Range: 0.0112. Min Range: -0.0112

Max Act: 0.0092. Min Act: -0.0006

Data Index: 722588 (C4 (Web Text))

Max Activating Token Index: 524

Text #4

Max Range: 0.0112. Min Range: -0.0112

Max Act: 0.0089. Min Act: -0.0006

Data Index: 784085 (C4 (Web Text))

Max Activating Token Index: 574

Text #5

Max Range: 0.0112. Min Range: -0.0112

Max Act: 0.0089. Min Act: -0.0006

Data Index: 1066119 (C4 (Web Text))

Max Activating Token Index: 906

Text #6

Max Range: 0.0112. Min Range: -0.0112

Max Act: 0.0088. Min Act: -0.0006

Data Index: 610118 (C4 (Web Text))

Max Activating Token Index: 382

Text #7

Max Range: 0.0112. Min Range: -0.0112

Max Act: 0.0088. Min Act: -0.0006

Data Index: 1057284 (C4 (Web Text))

Max Activating Token Index: 1014

Text #8

Max Range: 0.0112. Min Range: -0.0112

Max Act: 0.0086. Min Act: -0.0006

Data Index: 849914 (C4 (Web Text))

Max Activating Token Index: 204

Text #9

Max Range: 0.0112. Min Range: -0.0112

Max Act: 0.0081. Min Act: -0.0006

Data Index: 1159904 (C4 (Web Text))

Max Activating Token Index: 888

Text #10

Max Range: 0.0112. Min Range: -0.0112

Max Act: 0.0083. Min Act: -0.0006

Data Index: 1243733 (C4 (Web Text))

Max Activating Token Index: 572

Text #11

Max Range: 0.0112. Min Range: -0.0112

Max Act: 0.0084. Min Act: -0.0006

Data Index: 587498 (C4 (Web Text))

Max Activating Token Index: 149

Text #12

Max Range: 0.0112. Min Range: -0.0112

Max Act: 0.0083. Min Act: -0.0006

Data Index: 708540 (C4 (Web Text))

Max Activating Token Index: 166

Text #13

Max Range: 0.0112. Min Range: -0.0112

Max Act: 0.0080. Min Act: -0.0005

Data Index: 46410 (C4 (Web Text))

Max Activating Token Index: 8

Text #14

Max Range: 0.0112. Min Range: -0.0112

Max Act: 0.0079. Min Act: -0.0006

Data Index: 452387 (C4 (Web Text))

Max Activating Token Index: 507

Text #15

Max Range: 0.0112. Min Range: -0.0112

Max Act: 0.0080. Min Act: -0.0006

Data Index: 1296763 (C4 (Web Text))

Max Activating Token Index: 58

Text #16

Max Range: 0.0112. Min Range: -0.0112

Max Act: 0.0079. Min Act: -0.0006

Data Index: 7022 (C4 (Web Text))

Max Activating Token Index: 387

Text #17

Max Range: 0.0112. Min Range: -0.0112

Max Act: 0.0082. Min Act: -0.0006

Data Index: 1170020 (C4 (Web Text))

Max Activating Token Index: 537

Text #18

Max Range: 0.0112. Min Range: -0.0112

Max Act: 0.0080. Min Act: -0.0006

Data Index: 602207 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 0.0112. Min Range: -0.0112

Max Act: 0.0079. Min Act: -0.0006

Data Index: 803594 (C4 (Web Text))

Max Activating Token Index: 45