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

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

Neuron 4680 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: 4.8775. Min Range: -4.8775

Max Act: 4.5350. Min Act: -0.0000

Data Index: 43172 (C4 (Web Text))

Max Activating Token Index: 450

Text #1

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.8775. Min Act: -0.0000

Data Index: 97239 (C4 (Web Text))

Max Activating Token Index: 980

Text #2

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.2048. Min Act: -0.0000

Data Index: 698036 (C4 (Web Text))

Max Activating Token Index: 166

Text #3

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.5375. Min Act: -0.0000

Data Index: 849270 (C4 (Web Text))

Max Activating Token Index: 607

Text #4

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.4193. Min Act: -0.0000

Data Index: 972457 (C4 (Web Text))

Max Activating Token Index: 274

Text #5

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.1547. Min Act: -0.0000

Data Index: 72639 (C4 (Web Text))

Max Activating Token Index: 960

Text #6

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.3129. Min Act: -0.0000

Data Index: 1064670 (C4 (Web Text))

Max Activating Token Index: 899

Text #7

Max Range: 4.8775. Min Range: -4.8775

Max Act: 3.9574. Min Act: -0.0000

Data Index: 1167634 (C4 (Web Text))

Max Activating Token Index: 534

Text #8

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.2214. Min Act: -0.0001

Data Index: 1073039 (C4 (Web Text))

Max Activating Token Index: 336

Text #9

Max Range: 4.8775. Min Range: -4.8775

Max Act: 3.7033. Min Act: -0.0000

Data Index: 693396 (C4 (Web Text))

Max Activating Token Index: 423

Text #10

Max Range: 4.8775. Min Range: -4.8775

Max Act: 3.8137. Min Act: -0.0000

Data Index: 379422 (C4 (Web Text))

Max Activating Token Index: 932

Text #11

Max Range: 4.8775. Min Range: -4.8775

Max Act: 3.8205. Min Act: -0.0000

Data Index: 51311 (C4 (Web Text))

Max Activating Token Index: 4

Text #12

Max Range: 4.8775. Min Range: -4.8775

Max Act: 3.7899. Min Act: -0.0000

Data Index: 786233 (C4 (Web Text))

Max Activating Token Index: 902

Text #13

Max Range: 4.8775. Min Range: -4.8775

Max Act: 3.9101. Min Act: -0.0000

Data Index: 829544 (C4 (Web Text))

Max Activating Token Index: 166

Text #14

Max Range: 4.8775. Min Range: -4.8775

Max Act: 3.7206. Min Act: -0.0000

Data Index: 698356 (C4 (Web Text))

Max Activating Token Index: 928

Text #15

Max Range: 4.8775. Min Range: -4.8775

Max Act: 3.5146. Min Act: -0.0000

Data Index: 1050283 (C4 (Web Text))

Max Activating Token Index: 991

Text #16

Max Range: 4.8775. Min Range: -4.8775

Max Act: 3.4916. Min Act: -0.0000

Data Index: 917583 (C4 (Web Text))

Max Activating Token Index: 888

Text #17

Max Range: 4.8775. Min Range: -4.8775

Max Act: 3.7437. Min Act: -0.0000

Data Index: 611111 (C4 (Web Text))

Max Activating Token Index: 785

Text #18

Max Range: 4.8775. Min Range: -4.8775

Max Act: 3.3810. Min Act: -0.0000

Data Index: 853246 (C4 (Web Text))

Max Activating Token Index: 741

Text #19

Max Range: 4.8775. Min Range: -4.8775

Max Act: 3.5299. Min Act: -0.0000

Data Index: 29862 (C4 (Web Text))

Max Activating Token Index: 444