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

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

Neuron 3913 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5930. Min Range: -1.5930

Max Act: 1.5906. Min Act: -0.0000

Data Index: 473057 (C4 (Web Text))

Max Activating Token Index: 426

Text #1

Max Range: 1.5930. Min Range: -1.5930

Max Act: 1.5930. Min Act: -0.0000

Data Index: 582923 (C4 (Web Text))

Max Activating Token Index: 384

Text #2

Max Range: 1.5930. Min Range: -1.5930

Max Act: 1.4555. Min Act: -0.0000

Data Index: 1299409 (C4 (Web Text))

Max Activating Token Index: 632

Text #3

Max Range: 1.5930. Min Range: -1.5930

Max Act: 1.2994. Min Act: -0.0000

Data Index: 115120 (C4 (Web Text))

Max Activating Token Index: 39

Text #4

Max Range: 1.5930. Min Range: -1.5930

Max Act: 1.3187. Min Act: -0.0000

Data Index: 540703 (C4 (Web Text))

Max Activating Token Index: 603

Text #5

Max Range: 1.5930. Min Range: -1.5930

Max Act: 1.2158. Min Act: -0.0000

Data Index: 744205 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 1.5930. Min Range: -1.5930

Max Act: 1.2529. Min Act: -0.0000

Data Index: 1054681 (C4 (Web Text))

Max Activating Token Index: 339

Text #7

Max Range: 1.5930. Min Range: -1.5930

Max Act: 1.1192. Min Act: -0.0000

Data Index: 453199 (C4 (Web Text))

Max Activating Token Index: 169

Text #8

Max Range: 1.5930. Min Range: -1.5930

Max Act: 1.1174. Min Act: -0.0000

Data Index: 416857 (C4 (Web Text))

Max Activating Token Index: 1015

Text #9

Max Range: 1.5930. Min Range: -1.5930

Max Act: 1.0982. Min Act: -0.0000

Data Index: 201877 (C4 (Web Text))

Max Activating Token Index: 434

Text #10

Max Range: 1.5930. Min Range: -1.5930

Max Act: 1.0896. Min Act: -0.0000

Data Index: 809273 (C4 (Web Text))

Max Activating Token Index: 331

Text #11

Max Range: 1.5930. Min Range: -1.5930

Max Act: 1.0836. Min Act: -0.0000

Data Index: 72930 (C4 (Web Text))

Max Activating Token Index: 198

Text #12

Max Range: 1.5930. Min Range: -1.5930

Max Act: 0.9751. Min Act: -0.0000

Data Index: 1119842 (C4 (Web Text))

Max Activating Token Index: 89

Text #13

Max Range: 1.5930. Min Range: -1.5930

Max Act: 0.9934. Min Act: -0.0000

Data Index: 384385 (C4 (Web Text))

Max Activating Token Index: 756

Text #14

Max Range: 1.5930. Min Range: -1.5930

Max Act: 0.9703. Min Act: -0.0000

Data Index: 638541 (C4 (Web Text))

Max Activating Token Index: 382

Text #15

Max Range: 1.5930. Min Range: -1.5930

Max Act: 0.9274. Min Act: -0.0000

Data Index: 213203 (C4 (Web Text))

Max Activating Token Index: 885

Text #16

Max Range: 1.5930. Min Range: -1.5930

Max Act: 0.9480. Min Act: -0.0000

Data Index: 207241 (C4 (Web Text))

Max Activating Token Index: 515

Text #17

Max Range: 1.5930. Min Range: -1.5930

Max Act: 0.9661. Min Act: -0.0000

Data Index: 446340 (C4 (Web Text))

Max Activating Token Index: 195

Text #18

Max Range: 1.5930. Min Range: -1.5930

Max Act: 0.8930. Min Act: -0.0000

Data Index: 163598 (C4 (Web Text))

Max Activating Token Index: 749

Text #19

Max Range: 1.5930. Min Range: -1.5930

Max Act: 0.8820. Min Act: -0.0000

Data Index: 493914 (C4 (Web Text))

Max Activating Token Index: 126