Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3633 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.0272. Min Range: -2.0272

Max Act: 2.0272. Min Act: -0.0001

Data Index: 1421566 (Python Code)

Max Activating Token Index: 1018

Text #1

Max Range: 2.0272. Min Range: -2.0272

Max Act: 1.7030. Min Act: -0.0000

Data Index: 821 (C4 (Web Text))

Max Activating Token Index: 562

Text #2

Max Range: 2.0272. Min Range: -2.0272

Max Act: 1.4521. Min Act: -0.0000

Data Index: 1046698 (C4 (Web Text))

Max Activating Token Index: 607

Text #3

Max Range: 2.0272. Min Range: -2.0272

Max Act: 1.6539. Min Act: -0.0000

Data Index: 1445083 (Python Code)

Max Activating Token Index: 140

Text #4

Max Range: 2.0272. Min Range: -2.0272

Max Act: 1.3683. Min Act: -0.0000

Data Index: 1102431 (C4 (Web Text))

Max Activating Token Index: 633

Text #5

Max Range: 2.0272. Min Range: -2.0272

Max Act: 1.3751. Min Act: -0.0000

Data Index: 417062 (C4 (Web Text))

Max Activating Token Index: 774

Text #6

Max Range: 2.0272. Min Range: -2.0272

Max Act: 1.4565. Min Act: -0.0001

Data Index: 1274766 (C4 (Web Text))

Max Activating Token Index: 69

Text #7

Max Range: 2.0272. Min Range: -2.0272

Max Act: 1.3113. Min Act: -0.0000

Data Index: 824379 (C4 (Web Text))

Max Activating Token Index: 1021

Text #8

Max Range: 2.0272. Min Range: -2.0272

Max Act: 1.4948. Min Act: -0.0000

Data Index: 182900 (C4 (Web Text))

Max Activating Token Index: 633

Text #9

Max Range: 2.0272. Min Range: -2.0272

Max Act: 1.3175. Min Act: -0.0000

Data Index: 160114 (C4 (Web Text))

Max Activating Token Index: 736

Text #10

Max Range: 2.0272. Min Range: -2.0272

Max Act: 1.3892. Min Act: -0.0000

Data Index: 884922 (C4 (Web Text))

Max Activating Token Index: 267

Text #11

Max Range: 2.0272. Min Range: -2.0272

Max Act: 1.3683. Min Act: -0.0000

Data Index: 267151 (C4 (Web Text))

Max Activating Token Index: 1015

Text #12

Max Range: 2.0272. Min Range: -2.0272

Max Act: 1.3983. Min Act: -0.0000

Data Index: 1278642 (C4 (Web Text))

Max Activating Token Index: 179

Text #13

Max Range: 2.0272. Min Range: -2.0272

Max Act: 1.2987. Min Act: -0.0000

Data Index: 451483 (C4 (Web Text))

Max Activating Token Index: 570

Text #14

Max Range: 2.0272. Min Range: -2.0272

Max Act: 1.4018. Min Act: -0.0000

Data Index: 10402 (C4 (Web Text))

Max Activating Token Index: 97

Text #15

Max Range: 2.0272. Min Range: -2.0272

Max Act: 1.3630. Min Act: -0.0000

Data Index: 1331373 (C4 (Web Text))

Max Activating Token Index: 937

Text #16

Max Range: 2.0272. Min Range: -2.0272

Max Act: 1.2493. Min Act: -0.0000

Data Index: 1060948 (C4 (Web Text))

Max Activating Token Index: 480

Text #17

Max Range: 2.0272. Min Range: -2.0272

Max Act: 1.2037. Min Act: -0.0000

Data Index: 1383338 (Python Code)

Max Activating Token Index: 270

Text #18

Max Range: 2.0272. Min Range: -2.0272

Max Act: 1.2300. Min Act: -0.0000

Data Index: 119402 (C4 (Web Text))

Max Activating Token Index: 965

Text #19

Max Range: 2.0272. Min Range: -2.0272

Max Act: 1.1924. Min Act: -0.0000

Data Index: 471217 (C4 (Web Text))

Max Activating Token Index: 28