Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3563 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4316. Min Range: -0.4316

Max Act: 0.4293. Min Act: -0.0001

Data Index: 76667 (C4 (Web Text))

Max Activating Token Index: 60

Text #1

Max Range: 0.4316. Min Range: -0.4316

Max Act: 0.4316. Min Act: -0.0001

Data Index: 685346 (C4 (Web Text))

Max Activating Token Index: 596

Text #2

Max Range: 0.4316. Min Range: -0.4316

Max Act: 0.4017. Min Act: -0.0001

Data Index: 708809 (C4 (Web Text))

Max Activating Token Index: 945

Text #3

Max Range: 0.4316. Min Range: -0.4316

Max Act: 0.3915. Min Act: -0.0000

Data Index: 689249 (C4 (Web Text))

Max Activating Token Index: 141

Text #4

Max Range: 0.4316. Min Range: -0.4316

Max Act: 0.3909. Min Act: -0.0001

Data Index: 1327109 (C4 (Web Text))

Max Activating Token Index: 188

Text #5

Max Range: 0.4316. Min Range: -0.4316

Max Act: 0.3896. Min Act: -0.0000

Data Index: 857783 (C4 (Web Text))

Max Activating Token Index: 723

Text #6

Max Range: 0.4316. Min Range: -0.4316

Max Act: 0.3869. Min Act: -0.0000

Data Index: 61384 (C4 (Web Text))

Max Activating Token Index: 496

Text #7

Max Range: 0.4316. Min Range: -0.4316

Max Act: 0.3841. Min Act: -0.0000

Data Index: 1136507 (C4 (Web Text))

Max Activating Token Index: 157

Text #8

Max Range: 0.4316. Min Range: -0.4316

Max Act: 0.3816. Min Act: -0.0000

Data Index: 36551 (C4 (Web Text))

Max Activating Token Index: 176

Text #9

Max Range: 0.4316. Min Range: -0.4316

Max Act: 0.3792. Min Act: -0.0000

Data Index: 29157 (C4 (Web Text))

Max Activating Token Index: 377

Text #10

Max Range: 0.4316. Min Range: -0.4316

Max Act: 0.3790. Min Act: -0.0000

Data Index: 979685 (C4 (Web Text))

Max Activating Token Index: 409

Text #11

Max Range: 0.4316. Min Range: -0.4316

Max Act: 0.3607. Min Act: -0.0000

Data Index: 634081 (C4 (Web Text))

Max Activating Token Index: 391

Text #12

Max Range: 0.4316. Min Range: -0.4316

Max Act: 0.3465. Min Act: -0.0001

Data Index: 1143619 (C4 (Web Text))

Max Activating Token Index: 882

Text #13

Max Range: 0.4316. Min Range: -0.4316

Max Act: 0.3595. Min Act: -0.0000

Data Index: 648398 (C4 (Web Text))

Max Activating Token Index: 108

Text #14

Max Range: 0.4316. Min Range: -0.4316

Max Act: 0.3577. Min Act: -0.0000

Data Index: 1282134 (C4 (Web Text))

Max Activating Token Index: 403

Text #15

Max Range: 0.4316. Min Range: -0.4316

Max Act: 0.3556. Min Act: -0.0000

Data Index: 689564 (C4 (Web Text))

Max Activating Token Index: 593

Text #16

Max Range: 0.4316. Min Range: -0.4316

Max Act: 0.3774. Min Act: -0.0001

Data Index: 499827 (C4 (Web Text))

Max Activating Token Index: 889

Text #17

Max Range: 0.4316. Min Range: -0.4316

Max Act: 0.3536. Min Act: -0.0000

Data Index: 554313 (C4 (Web Text))

Max Activating Token Index: 225

Text #18

Max Range: 0.4316. Min Range: -0.4316

Max Act: 0.3449. Min Act: -0.0000

Data Index: 959600 (C4 (Web Text))

Max Activating Token Index: 331

Text #19

Max Range: 0.4316. Min Range: -0.4316

Max Act: 0.3371. Min Act: -0.0000

Data Index: 420069 (C4 (Web Text))

Max Activating Token Index: 408