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

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

Neuron 3584 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4993. Min Range: -0.4993

Max Act: 0.4840. Min Act: -0.0000

Data Index: 864523 (C4 (Web Text))

Max Activating Token Index: 1001

Text #1

Max Range: 0.4993. Min Range: -0.4993

Max Act: 0.4993. Min Act: -0.0000

Data Index: 36877 (C4 (Web Text))

Max Activating Token Index: 263

Text #2

Max Range: 0.4993. Min Range: -0.4993

Max Act: 0.4647. Min Act: -0.0000

Data Index: 1165086 (C4 (Web Text))

Max Activating Token Index: 782

Text #3

Max Range: 0.4993. Min Range: -0.4993

Max Act: 0.4865. Min Act: -0.0000

Data Index: 1016600 (C4 (Web Text))

Max Activating Token Index: 847

Text #4

Max Range: 0.4993. Min Range: -0.4993

Max Act: 0.4045. Min Act: -0.0000

Data Index: 829993 (C4 (Web Text))

Max Activating Token Index: 222

Text #5

Max Range: 0.4993. Min Range: -0.4993

Max Act: 0.4103. Min Act: -0.0000

Data Index: 854123 (C4 (Web Text))

Max Activating Token Index: 902

Text #6

Max Range: 0.4993. Min Range: -0.4993

Max Act: 0.4177. Min Act: -0.0000

Data Index: 456353 (C4 (Web Text))

Max Activating Token Index: 989

Text #7

Max Range: 0.4993. Min Range: -0.4993

Max Act: 0.4170. Min Act: -0.0000

Data Index: 129026 (C4 (Web Text))

Max Activating Token Index: 143

Text #8

Max Range: 0.4993. Min Range: -0.4993

Max Act: 0.4009. Min Act: -0.0000

Data Index: 1029684 (C4 (Web Text))

Max Activating Token Index: 667

Text #9

Max Range: 0.4993. Min Range: -0.4993

Max Act: 0.3753. Min Act: -0.0000

Data Index: 48680 (C4 (Web Text))

Max Activating Token Index: 807

Text #10

Max Range: 0.4993. Min Range: -0.4993

Max Act: 0.3983. Min Act: -0.0000

Data Index: 227774 (C4 (Web Text))

Max Activating Token Index: 282

Text #11

Max Range: 0.4993. Min Range: -0.4993

Max Act: 0.3844. Min Act: -0.0000

Data Index: 511402 (C4 (Web Text))

Max Activating Token Index: 728

Text #12

Max Range: 0.4993. Min Range: -0.4993

Max Act: 0.3753. Min Act: -0.0000

Data Index: 96939 (C4 (Web Text))

Max Activating Token Index: 884

Text #13

Max Range: 0.4993. Min Range: -0.4993

Max Act: 0.3625. Min Act: -0.0000

Data Index: 172099 (C4 (Web Text))

Max Activating Token Index: 313

Text #14

Max Range: 0.4993. Min Range: -0.4993

Max Act: 0.3567. Min Act: -0.0000

Data Index: 1046516 (C4 (Web Text))

Max Activating Token Index: 104

Text #15

Max Range: 0.4993. Min Range: -0.4993

Max Act: 0.3526. Min Act: -0.0000

Data Index: 740005 (C4 (Web Text))

Max Activating Token Index: 273

Text #16

Max Range: 0.4993. Min Range: -0.4993

Max Act: 0.3722. Min Act: -0.0000

Data Index: 738248 (C4 (Web Text))

Max Activating Token Index: 815

Text #17

Max Range: 0.4993. Min Range: -0.4993

Max Act: 0.3576. Min Act: -0.0000

Data Index: 1190073 (C4 (Web Text))

Max Activating Token Index: 77

Text #18

Max Range: 0.4993. Min Range: -0.4993

Max Act: 0.3520. Min Act: -0.0000

Data Index: 1196056 (C4 (Web Text))

Max Activating Token Index: 976

Text #19

Max Range: 0.4993. Min Range: -0.4993

Max Act: 0.3545. Min Act: -0.0000

Data Index: 369452 (C4 (Web Text))

Max Activating Token Index: 589