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

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

Neuron 390 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: 0.0070. Min Range: -0.0070

Max Act: 0.0070. Min Act: -0.0006

Data Index: 639913 (C4 (Web Text))

Max Activating Token Index: 436

Text #1

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0068. Min Act: -0.0006

Data Index: 1193380 (C4 (Web Text))

Max Activating Token Index: 850

Text #2

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0064. Min Act: -0.0006

Data Index: 1351241 (C4 (Web Text))

Max Activating Token Index: 795

Text #3

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0065. Min Act: -0.0006

Data Index: 757427 (C4 (Web Text))

Max Activating Token Index: 803

Text #4

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0062. Min Act: -0.0006

Data Index: 197094 (C4 (Web Text))

Max Activating Token Index: 769

Text #5

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0063. Min Act: -0.0006

Data Index: 1042611 (C4 (Web Text))

Max Activating Token Index: 284

Text #6

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0062. Min Act: -0.0006

Data Index: 99062 (C4 (Web Text))

Max Activating Token Index: 788

Text #7

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0062. Min Act: -0.0006

Data Index: 1133782 (C4 (Web Text))

Max Activating Token Index: 362

Text #8

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0062. Min Act: -0.0006

Data Index: 903600 (C4 (Web Text))

Max Activating Token Index: 867

Text #9

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0062. Min Act: -0.0006

Data Index: 985897 (C4 (Web Text))

Max Activating Token Index: 857

Text #10

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0062. Min Act: -0.0006

Data Index: 329997 (C4 (Web Text))

Max Activating Token Index: 818

Text #11

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0062. Min Act: -0.0006

Data Index: 1277264 (C4 (Web Text))

Max Activating Token Index: 812

Text #12

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0061. Min Act: -0.0006

Data Index: 538236 (C4 (Web Text))

Max Activating Token Index: 429

Text #13

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0061. Min Act: -0.0006

Data Index: 596957 (C4 (Web Text))

Max Activating Token Index: 404

Text #14

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0061. Min Act: -0.0006

Data Index: 673129 (C4 (Web Text))

Max Activating Token Index: 322

Text #15

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0061. Min Act: -0.0006

Data Index: 873392 (C4 (Web Text))

Max Activating Token Index: 437

Text #16

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0060. Min Act: -0.0007

Data Index: 848773 (C4 (Web Text))

Max Activating Token Index: 313

Text #17

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0061. Min Act: -0.0006

Data Index: 14478 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0060. Min Act: -0.0006

Data Index: 925366 (C4 (Web Text))

Max Activating Token Index: 922

Text #19

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0060. Min Act: -0.0006

Data Index: 606410 (C4 (Web Text))

Max Activating Token Index: 726