Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 451 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0307. Min Act: -0.0001

Data Index: 573440 (C4 (Web Text))

Max Activating Token Index: 330

Text #1

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0304. Min Act: -0.0001

Data Index: 593933 (C4 (Web Text))

Max Activating Token Index: 622

Text #2

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0092. Min Act: -0.0001

Data Index: 240607 (C4 (Web Text))

Max Activating Token Index: 141

Text #3

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0083. Min Act: -0.0000

Data Index: 1352568 (C4 (Web Text))

Max Activating Token Index: 269

Text #4

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0079. Min Act: -0.0001

Data Index: 470829 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0078. Min Act: -0.0000

Data Index: 57880 (C4 (Web Text))

Max Activating Token Index: 234

Text #6

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0080. Min Act: -0.0000

Data Index: 803970 (C4 (Web Text))

Max Activating Token Index: 222

Text #7

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0077. Min Act: -0.0000

Data Index: 194320 (C4 (Web Text))

Max Activating Token Index: 168

Text #8

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0071. Min Act: -0.0000

Data Index: 175038 (C4 (Web Text))

Max Activating Token Index: 199

Text #9

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0074. Min Act: -0.0000

Data Index: 1537250 (Python Code)

Max Activating Token Index: 173

Text #10

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0070. Min Act: -0.0001

Data Index: 537548 (C4 (Web Text))

Max Activating Token Index: 279

Text #11

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0074. Min Act: -0.0000

Data Index: 461473 (C4 (Web Text))

Max Activating Token Index: 132

Text #12

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0073. Min Act: -0.0001

Data Index: 188807 (C4 (Web Text))

Max Activating Token Index: 218

Text #13

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0075. Min Act: -0.0000

Data Index: 766379 (C4 (Web Text))

Max Activating Token Index: 201

Text #14

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0070. Min Act: -0.0000

Data Index: 1019418 (C4 (Web Text))

Max Activating Token Index: 259

Text #15

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0070. Min Act: -0.0001

Data Index: 552896 (C4 (Web Text))

Max Activating Token Index: 311

Text #16

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0072. Min Act: -0.0000

Data Index: 74596 (C4 (Web Text))

Max Activating Token Index: 161

Text #17

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0076. Min Act: -0.0001

Data Index: 251520 (C4 (Web Text))

Max Activating Token Index: 200

Text #18

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0069. Min Act: -0.0000

Data Index: 1292619 (C4 (Web Text))

Max Activating Token Index: 262

Text #19

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0072. Min Act: -0.0000

Data Index: 982916 (C4 (Web Text))

Max Activating Token Index: 205