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

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

Neuron 4706 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.5060. Min Act: -0.0000

Data Index: 890671 (C4 (Web Text))

Max Activating Token Index: 160

Text #1

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4551. Min Act: -0.0000

Data Index: 442400 (C4 (Web Text))

Max Activating Token Index: 186

Text #2

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4634. Min Act: -0.0000

Data Index: 1099059 (C4 (Web Text))

Max Activating Token Index: 711

Text #3

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4697. Min Act: -0.0000

Data Index: 622181 (C4 (Web Text))

Max Activating Token Index: 45

Text #4

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4298. Min Act: -0.0000

Data Index: 423064 (C4 (Web Text))

Max Activating Token Index: 52

Text #5

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4674. Min Act: -0.0000

Data Index: 453735 (C4 (Web Text))

Max Activating Token Index: 41

Text #6

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4309. Min Act: -0.0000

Data Index: 97906 (C4 (Web Text))

Max Activating Token Index: 112

Text #7

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4288. Min Act: -0.0000

Data Index: 222099 (C4 (Web Text))

Max Activating Token Index: 88

Text #8

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4097. Min Act: -0.0000

Data Index: 750154 (C4 (Web Text))

Max Activating Token Index: 119

Text #9

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4089. Min Act: -0.0000

Data Index: 799042 (C4 (Web Text))

Max Activating Token Index: 184

Text #10

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4086. Min Act: -0.0000

Data Index: 179755 (C4 (Web Text))

Max Activating Token Index: 240

Text #11

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.3843. Min Act: -0.0000

Data Index: 687440 (C4 (Web Text))

Max Activating Token Index: 290

Text #12

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.3825. Min Act: -0.0000

Data Index: 664227 (C4 (Web Text))

Max Activating Token Index: 39

Text #13

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.3716. Min Act: -0.0000

Data Index: 484944 (C4 (Web Text))

Max Activating Token Index: 87

Text #14

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.3532. Min Act: -0.0000

Data Index: 64276 (C4 (Web Text))

Max Activating Token Index: 864

Text #15

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.3709. Min Act: -0.0000

Data Index: 1362142 (Python Code)

Max Activating Token Index: 935

Text #16

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.3800. Min Act: -0.0000

Data Index: 588271 (C4 (Web Text))

Max Activating Token Index: 249

Text #17

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.3788. Min Act: -0.0000

Data Index: 886938 (C4 (Web Text))

Max Activating Token Index: 135

Text #18

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.3785. Min Act: -0.0000

Data Index: 1280708 (C4 (Web Text))

Max Activating Token Index: 129

Text #19

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.3618. Min Act: -0.0000

Data Index: 1128895 (C4 (Web Text))

Max Activating Token Index: 237