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

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

Neuron 3904 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1931. Min Range: -1.1931

Max Act: 1.1931. Min Act: -0.0001

Data Index: 1363344 (Python Code)

Max Activating Token Index: 86

Text #1

Max Range: 1.1931. Min Range: -1.1931

Max Act: 1.1319. Min Act: -0.0001

Data Index: 1652722 (Python Code)

Max Activating Token Index: 851

Text #2

Max Range: 1.1931. Min Range: -1.1931

Max Act: 0.9847. Min Act: -0.0001

Data Index: 1375609 (Python Code)

Max Activating Token Index: 165

Text #3

Max Range: 1.1931. Min Range: -1.1931

Max Act: 1.0052. Min Act: -0.0001

Data Index: 1506123 (Python Code)

Max Activating Token Index: 171

Text #4

Max Range: 1.1931. Min Range: -1.1931

Max Act: 0.9903. Min Act: -0.0001

Data Index: 1652053 (Python Code)

Max Activating Token Index: 354

Text #5

Max Range: 1.1931. Min Range: -1.1931

Max Act: 0.9814. Min Act: -0.0001

Data Index: 1481359 (Python Code)

Max Activating Token Index: 521

Text #6

Max Range: 1.1931. Min Range: -1.1931

Max Act: 0.9384. Min Act: -0.0001

Data Index: 1555335 (Python Code)

Max Activating Token Index: 151

Text #7

Max Range: 1.1931. Min Range: -1.1931

Max Act: 0.9261. Min Act: -0.0001

Data Index: 1390186 (Python Code)

Max Activating Token Index: 615

Text #8

Max Range: 1.1931. Min Range: -1.1931

Max Act: 0.9545. Min Act: -0.0001

Data Index: 1442999 (Python Code)

Max Activating Token Index: 528

Text #9

Max Range: 1.1931. Min Range: -1.1931

Max Act: 0.8870. Min Act: -0.0001

Data Index: 1516591 (Python Code)

Max Activating Token Index: 232

Text #10

Max Range: 1.1931. Min Range: -1.1931

Max Act: 0.9036. Min Act: -0.0001

Data Index: 78648 (C4 (Web Text))

Max Activating Token Index: 175

Text #11

Max Range: 1.1931. Min Range: -1.1931

Max Act: 0.9011. Min Act: -0.0001

Data Index: 1520485 (Python Code)

Max Activating Token Index: 10

Text #12

Max Range: 1.1931. Min Range: -1.1931

Max Act: 0.8799. Min Act: -0.0001

Data Index: 1595736 (Python Code)

Max Activating Token Index: 52

Text #13

Max Range: 1.1931. Min Range: -1.1931

Max Act: 0.9014. Min Act: -0.0001

Data Index: 1360056 (Python Code)

Max Activating Token Index: 414

Text #14

Max Range: 1.1931. Min Range: -1.1931

Max Act: 0.8447. Min Act: -0.0001

Data Index: 1642616 (Python Code)

Max Activating Token Index: 272

Text #15

Max Range: 1.1931. Min Range: -1.1931

Max Act: 0.8858. Min Act: -0.0001

Data Index: 1630434 (Python Code)

Max Activating Token Index: 544

Text #16

Max Range: 1.1931. Min Range: -1.1931

Max Act: 0.8751. Min Act: -0.0001

Data Index: 307271 (C4 (Web Text))

Max Activating Token Index: 1009

Text #17

Max Range: 1.1931. Min Range: -1.1931

Max Act: 0.8851. Min Act: -0.0001

Data Index: 1368935 (Python Code)

Max Activating Token Index: 910

Text #18

Max Range: 1.1931. Min Range: -1.1931

Max Act: 0.8165. Min Act: -0.0001

Data Index: 1511417 (Python Code)

Max Activating Token Index: 659

Text #19

Max Range: 1.1931. Min Range: -1.1931

Max Act: 0.8376. Min Act: -0.0001

Data Index: 1582065 (Python Code)

Max Activating Token Index: 175