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

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

Neuron 216 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: 1.2923. Min Range: -1.2923

Max Act: 1.2923. Min Act: -0.0001

Data Index: 1024743 (C4 (Web Text))

Max Activating Token Index: 720

Text #1

Max Range: 1.2923. Min Range: -1.2923

Max Act: 1.2267. Min Act: -0.0001

Data Index: 1334825 (C4 (Web Text))

Max Activating Token Index: 185

Text #2

Max Range: 1.2923. Min Range: -1.2923

Max Act: 1.2598. Min Act: -0.0001

Data Index: 1010052 (C4 (Web Text))

Max Activating Token Index: 800

Text #3

Max Range: 1.2923. Min Range: -1.2923

Max Act: 1.1629. Min Act: -0.0001

Data Index: 678293 (C4 (Web Text))

Max Activating Token Index: 41

Text #4

Max Range: 1.2923. Min Range: -1.2923

Max Act: 1.1987. Min Act: -0.0001

Data Index: 1117307 (C4 (Web Text))

Max Activating Token Index: 783

Text #5

Max Range: 1.2923. Min Range: -1.2923

Max Act: 1.0701. Min Act: -0.0001

Data Index: 504644 (C4 (Web Text))

Max Activating Token Index: 809

Text #6

Max Range: 1.2923. Min Range: -1.2923

Max Act: 1.0825. Min Act: -0.0001

Data Index: 892633 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 1.2923. Min Range: -1.2923

Max Act: 0.9575. Min Act: -0.0001

Data Index: 776887 (C4 (Web Text))

Max Activating Token Index: 985

Text #8

Max Range: 1.2923. Min Range: -1.2923

Max Act: 0.9760. Min Act: -0.0001

Data Index: 550163 (C4 (Web Text))

Max Activating Token Index: 259

Text #9

Max Range: 1.2923. Min Range: -1.2923

Max Act: 0.9497. Min Act: -0.0001

Data Index: 1121294 (C4 (Web Text))

Max Activating Token Index: 369

Text #10

Max Range: 1.2923. Min Range: -1.2923

Max Act: 0.9712. Min Act: -0.0001

Data Index: 983224 (C4 (Web Text))

Max Activating Token Index: 613

Text #11

Max Range: 1.2923. Min Range: -1.2923

Max Act: 0.9353. Min Act: -0.0001

Data Index: 1248514 (C4 (Web Text))

Max Activating Token Index: 525

Text #12

Max Range: 1.2923. Min Range: -1.2923

Max Act: 0.9276. Min Act: -0.0001

Data Index: 181937 (C4 (Web Text))

Max Activating Token Index: 616

Text #13

Max Range: 1.2923. Min Range: -1.2923

Max Act: 0.8568. Min Act: -0.0001

Data Index: 1335295 (C4 (Web Text))

Max Activating Token Index: 203

Text #14

Max Range: 1.2923. Min Range: -1.2923

Max Act: 0.8824. Min Act: -0.0001

Data Index: 203309 (C4 (Web Text))

Max Activating Token Index: 523

Text #15

Max Range: 1.2923. Min Range: -1.2923

Max Act: 0.9078. Min Act: -0.0001

Data Index: 859048 (C4 (Web Text))

Max Activating Token Index: 72

Text #16

Max Range: 1.2923. Min Range: -1.2923

Max Act: 0.9104. Min Act: -0.0001

Data Index: 389589 (C4 (Web Text))

Max Activating Token Index: 601

Text #17

Max Range: 1.2923. Min Range: -1.2923

Max Act: 0.8479. Min Act: -0.0001

Data Index: 993393 (C4 (Web Text))

Max Activating Token Index: 103

Text #18

Max Range: 1.2923. Min Range: -1.2923

Max Act: 0.9011. Min Act: -0.0001

Data Index: 418144 (C4 (Web Text))

Max Activating Token Index: 116

Text #19

Max Range: 1.2923. Min Range: -1.2923

Max Act: 0.9014. Min Act: -0.0001

Data Index: 734505 (C4 (Web Text))

Max Activating Token Index: 237