Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 2007 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0101. Min Act: -0.0006

Data Index: 338846 (C4 (Web Text))

Max Activating Token Index: 888

Text #1

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0097. Min Act: -0.0006

Data Index: 87503 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0092. Min Act: -0.0006

Data Index: 1064025 (C4 (Web Text))

Max Activating Token Index: 852

Text #3

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0093. Min Act: -0.0006

Data Index: 641791 (C4 (Web Text))

Max Activating Token Index: 278

Text #4

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0090. Min Act: -0.0006

Data Index: 233129 (C4 (Web Text))

Max Activating Token Index: 43

Text #5

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0092. Min Act: -0.0006

Data Index: 1061366 (C4 (Web Text))

Max Activating Token Index: 554

Text #6

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0090. Min Act: -0.0006

Data Index: 315156 (C4 (Web Text))

Max Activating Token Index: 442

Text #7

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0090. Min Act: -0.0006

Data Index: 876768 (C4 (Web Text))

Max Activating Token Index: 459

Text #8

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0085. Min Act: -0.0006

Data Index: 875487 (C4 (Web Text))

Max Activating Token Index: 972

Text #9

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0088. Min Act: -0.0006

Data Index: 831090 (C4 (Web Text))

Max Activating Token Index: 301

Text #10

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0092. Min Act: -0.0006

Data Index: 1054996 (C4 (Web Text))

Max Activating Token Index: 163

Text #11

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0087. Min Act: -0.0006

Data Index: 1119603 (C4 (Web Text))

Max Activating Token Index: 637

Text #12

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0088. Min Act: -0.0006

Data Index: 1018082 (C4 (Web Text))

Max Activating Token Index: 823

Text #13

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0090. Min Act: -0.0006

Data Index: 625820 (C4 (Web Text))

Max Activating Token Index: 611

Text #14

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0087. Min Act: -0.0006

Data Index: 928214 (C4 (Web Text))

Max Activating Token Index: 986

Text #15

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0085. Min Act: -0.0006

Data Index: 875273 (C4 (Web Text))

Max Activating Token Index: 205

Text #16

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0090. Min Act: -0.0006

Data Index: 1267608 (C4 (Web Text))

Max Activating Token Index: 597

Text #17

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0088. Min Act: -0.0006

Data Index: 538051 (C4 (Web Text))

Max Activating Token Index: 630

Text #18

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0081. Min Act: -0.0006

Data Index: 607291 (C4 (Web Text))

Max Activating Token Index: 453

Text #19

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0083. Min Act: -0.0006

Data Index: 80167 (C4 (Web Text))

Max Activating Token Index: 726