Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2224 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7968. Min Range: -0.7968

Max Act: 0.7968. Min Act: -0.0003

Data Index: 976923 (C4 (Web Text))

Max Activating Token Index: 446

Text #1

Max Range: 0.7968. Min Range: -0.7968

Max Act: 0.7269. Min Act: -0.0003

Data Index: 1026129 (C4 (Web Text))

Max Activating Token Index: 936

Text #2

Max Range: 0.7968. Min Range: -0.7968

Max Act: 0.6773. Min Act: -0.0003

Data Index: 84855 (C4 (Web Text))

Max Activating Token Index: 785

Text #3

Max Range: 0.7968. Min Range: -0.7968

Max Act: 0.6442. Min Act: -0.0003

Data Index: 552585 (C4 (Web Text))

Max Activating Token Index: 561

Text #4

Max Range: 0.7968. Min Range: -0.7968

Max Act: 0.7466. Min Act: -0.0003

Data Index: 1356044 (C4 (Web Text))

Max Activating Token Index: 400

Text #5

Max Range: 0.7968. Min Range: -0.7968

Max Act: 0.6392. Min Act: -0.0003

Data Index: 106234 (C4 (Web Text))

Max Activating Token Index: 913

Text #6

Max Range: 0.7968. Min Range: -0.7968

Max Act: 0.6088. Min Act: -0.0003

Data Index: 1111159 (C4 (Web Text))

Max Activating Token Index: 390

Text #7

Max Range: 0.7968. Min Range: -0.7968

Max Act: 0.5861. Min Act: -0.0003

Data Index: 696274 (C4 (Web Text))

Max Activating Token Index: 628

Text #8

Max Range: 0.7968. Min Range: -0.7968

Max Act: 0.5488. Min Act: -0.0003

Data Index: 408316 (C4 (Web Text))

Max Activating Token Index: 721

Text #9

Max Range: 0.7968. Min Range: -0.7968

Max Act: 0.5918. Min Act: -0.0003

Data Index: 1377496 (Python Code)

Max Activating Token Index: 201

Text #10

Max Range: 0.7968. Min Range: -0.7968

Max Act: 0.5979. Min Act: -0.0003

Data Index: 429623 (C4 (Web Text))

Max Activating Token Index: 856

Text #11

Max Range: 0.7968. Min Range: -0.7968

Max Act: 0.5951. Min Act: -0.0003

Data Index: 1586817 (Python Code)

Max Activating Token Index: 556

Text #12

Max Range: 0.7968. Min Range: -0.7968

Max Act: 0.5561. Min Act: -0.0003

Data Index: 423411 (C4 (Web Text))

Max Activating Token Index: 387

Text #13

Max Range: 0.7968. Min Range: -0.7968

Max Act: 0.5715. Min Act: -0.0003

Data Index: 1197493 (C4 (Web Text))

Max Activating Token Index: 978

Text #14

Max Range: 0.7968. Min Range: -0.7968

Max Act: 0.5889. Min Act: -0.0003

Data Index: 1365604 (Python Code)

Max Activating Token Index: 563

Text #15

Max Range: 0.7968. Min Range: -0.7968

Max Act: 0.4892. Min Act: -0.0003

Data Index: 1038604 (C4 (Web Text))

Max Activating Token Index: 364

Text #16

Max Range: 0.7968. Min Range: -0.7968

Max Act: 0.5360. Min Act: -0.0003

Data Index: 1473985 (Python Code)

Max Activating Token Index: 132

Text #17

Max Range: 0.7968. Min Range: -0.7968

Max Act: 0.5679. Min Act: -0.0003

Data Index: 320691 (C4 (Web Text))

Max Activating Token Index: 894

Text #18

Max Range: 0.7968. Min Range: -0.7968

Max Act: 0.5355. Min Act: -0.0003

Data Index: 1470953 (Python Code)

Max Activating Token Index: 832

Text #19

Max Range: 0.7968. Min Range: -0.7968

Max Act: 0.5130. Min Act: -0.0003

Data Index: 1531927 (Python Code)

Max Activating Token Index: 356