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

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

Neuron 2061 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4829. Min Range: -0.4829

Max Act: 0.4829. Min Act: -0.0001

Data Index: 57468 (C4 (Web Text))

Max Activating Token Index: 987

Text #1

Max Range: 0.4829. Min Range: -0.4829

Max Act: 0.4016. Min Act: -0.0001

Data Index: 336778 (C4 (Web Text))

Max Activating Token Index: 88

Text #2

Max Range: 0.4829. Min Range: -0.4829

Max Act: 0.3359. Min Act: -0.0000

Data Index: 753678 (C4 (Web Text))

Max Activating Token Index: 277

Text #3

Max Range: 0.4829. Min Range: -0.4829

Max Act: 0.3416. Min Act: -0.0001

Data Index: 154575 (C4 (Web Text))

Max Activating Token Index: 538

Text #4

Max Range: 0.4829. Min Range: -0.4829

Max Act: 0.3547. Min Act: -0.0001

Data Index: 27356 (C4 (Web Text))

Max Activating Token Index: 630

Text #5

Max Range: 0.4829. Min Range: -0.4829

Max Act: 0.3224. Min Act: -0.0000

Data Index: 632964 (C4 (Web Text))

Max Activating Token Index: 970

Text #6

Max Range: 0.4829. Min Range: -0.4829

Max Act: 0.3343. Min Act: -0.0001

Data Index: 453737 (C4 (Web Text))

Max Activating Token Index: 410

Text #7

Max Range: 0.4829. Min Range: -0.4829

Max Act: 0.3060. Min Act: -0.0001

Data Index: 862621 (C4 (Web Text))

Max Activating Token Index: 622

Text #8

Max Range: 0.4829. Min Range: -0.4829

Max Act: 0.3069. Min Act: -0.0001

Data Index: 388875 (C4 (Web Text))

Max Activating Token Index: 506

Text #9

Max Range: 0.4829. Min Range: -0.4829

Max Act: 0.2914. Min Act: -0.0001

Data Index: 508766 (C4 (Web Text))

Max Activating Token Index: 85

Text #10

Max Range: 0.4829. Min Range: -0.4829

Max Act: 0.2766. Min Act: -0.0001

Data Index: 1042952 (C4 (Web Text))

Max Activating Token Index: 332

Text #11

Max Range: 0.4829. Min Range: -0.4829

Max Act: 0.2850. Min Act: -0.0001

Data Index: 729714 (C4 (Web Text))

Max Activating Token Index: 878

Text #12

Max Range: 0.4829. Min Range: -0.4829

Max Act: 0.2726. Min Act: -0.0001

Data Index: 81169 (C4 (Web Text))

Max Activating Token Index: 243

Text #13

Max Range: 0.4829. Min Range: -0.4829

Max Act: 0.2755. Min Act: -0.0001

Data Index: 1179488 (C4 (Web Text))

Max Activating Token Index: 320

Text #14

Max Range: 0.4829. Min Range: -0.4829

Max Act: 0.2715. Min Act: -0.0000

Data Index: 818770 (C4 (Web Text))

Max Activating Token Index: 986

Text #15

Max Range: 0.4829. Min Range: -0.4829

Max Act: 0.2898. Min Act: -0.0001

Data Index: 629195 (C4 (Web Text))

Max Activating Token Index: 1009

Text #16

Max Range: 0.4829. Min Range: -0.4829

Max Act: 0.2823. Min Act: -0.0001

Data Index: 1216216 (C4 (Web Text))

Max Activating Token Index: 87

Text #17

Max Range: 0.4829. Min Range: -0.4829

Max Act: 0.2672. Min Act: -0.0001

Data Index: 747512 (C4 (Web Text))

Max Activating Token Index: 608

Text #18

Max Range: 0.4829. Min Range: -0.4829

Max Act: 0.2564. Min Act: -0.0000

Data Index: 192031 (C4 (Web Text))

Max Activating Token Index: 592

Text #19

Max Range: 0.4829. Min Range: -0.4829

Max Act: 0.2748. Min Act: -0.0001

Data Index: 1224346 (C4 (Web Text))

Max Activating Token Index: 170