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

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

Neuron 3360 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0101. Min Act: -0.0000

Data Index: 913316 (C4 (Web Text))

Max Activating Token Index: 397

Text #1

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0097. Min Act: -0.0000

Data Index: 1306736 (C4 (Web Text))

Max Activating Token Index: 462

Text #2

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0096. Min Act: -0.0000

Data Index: 4743 (C4 (Web Text))

Max Activating Token Index: 564

Text #3

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0097. Min Act: 0.0000

Data Index: 657431 (C4 (Web Text))

Max Activating Token Index: 454

Text #4

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0092. Min Act: 0.0000

Data Index: 1179796 (C4 (Web Text))

Max Activating Token Index: 334

Text #5

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0088. Min Act: 0.0000

Data Index: 97831 (C4 (Web Text))

Max Activating Token Index: 465

Text #6

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0088. Min Act: -0.0000

Data Index: 1463000 (Python Code)

Max Activating Token Index: 448

Text #7

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0087. Min Act: 0.0000

Data Index: 561101 (C4 (Web Text))

Max Activating Token Index: 498

Text #8

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0087. Min Act: 0.0000

Data Index: 1082862 (C4 (Web Text))

Max Activating Token Index: 400

Text #9

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0087. Min Act: -0.0000

Data Index: 423059 (C4 (Web Text))

Max Activating Token Index: 230

Text #10

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0086. Min Act: -0.0000

Data Index: 1321889 (C4 (Web Text))

Max Activating Token Index: 514

Text #11

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0090. Min Act: 0.0001

Data Index: 233002 (C4 (Web Text))

Max Activating Token Index: 488

Text #12

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0082. Min Act: 0.0000

Data Index: 35409 (C4 (Web Text))

Max Activating Token Index: 413

Text #13

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0083. Min Act: -0.0000

Data Index: 1586697 (Python Code)

Max Activating Token Index: 425

Text #14

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0085. Min Act: 0.0000

Data Index: 1355403 (C4 (Web Text))

Max Activating Token Index: 362

Text #15

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0085. Min Act: -0.0000

Data Index: 695088 (C4 (Web Text))

Max Activating Token Index: 505

Text #16

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0082. Min Act: 0.0000

Data Index: 1367422 (Python Code)

Max Activating Token Index: 470

Text #17

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0083. Min Act: 0.0000

Data Index: 601718 (C4 (Web Text))

Max Activating Token Index: 501

Text #18

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0083. Min Act: -0.0000

Data Index: 1623361 (Python Code)

Max Activating Token Index: 560

Text #19

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0083. Min Act: 0.0000

Data Index: 963914 (C4 (Web Text))

Max Activating Token Index: 595