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

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

Neuron 3434 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4011. Min Range: -0.4011

Max Act: 0.4011. Min Act: -0.0000

Data Index: 989347 (C4 (Web Text))

Max Activating Token Index: 489

Text #1

Max Range: 0.4011. Min Range: -0.4011

Max Act: 0.3685. Min Act: -0.0000

Data Index: 82829 (C4 (Web Text))

Max Activating Token Index: 260

Text #2

Max Range: 0.4011. Min Range: -0.4011

Max Act: 0.3418. Min Act: -0.0000

Data Index: 1061660 (C4 (Web Text))

Max Activating Token Index: 397

Text #3

Max Range: 0.4011. Min Range: -0.4011

Max Act: 0.2998. Min Act: -0.0000

Data Index: 388798 (C4 (Web Text))

Max Activating Token Index: 693

Text #4

Max Range: 0.4011. Min Range: -0.4011

Max Act: 0.3082. Min Act: -0.0000

Data Index: 987797 (C4 (Web Text))

Max Activating Token Index: 847

Text #5

Max Range: 0.4011. Min Range: -0.4011

Max Act: 0.2888. Min Act: -0.0000

Data Index: 164083 (C4 (Web Text))

Max Activating Token Index: 959

Text #6

Max Range: 0.4011. Min Range: -0.4011

Max Act: 0.3388. Min Act: -0.0000

Data Index: 17936 (C4 (Web Text))

Max Activating Token Index: 186

Text #7

Max Range: 0.4011. Min Range: -0.4011

Max Act: 0.3150. Min Act: -0.0000

Data Index: 1349223 (C4 (Web Text))

Max Activating Token Index: 662

Text #8

Max Range: 0.4011. Min Range: -0.4011

Max Act: 0.3153. Min Act: -0.0000

Data Index: 1046508 (C4 (Web Text))

Max Activating Token Index: 724

Text #9

Max Range: 0.4011. Min Range: -0.4011

Max Act: 0.2916. Min Act: -0.0000

Data Index: 1107146 (C4 (Web Text))

Max Activating Token Index: 640

Text #10

Max Range: 0.4011. Min Range: -0.4011

Max Act: 0.2930. Min Act: -0.0000

Data Index: 698032 (C4 (Web Text))

Max Activating Token Index: 420

Text #11

Max Range: 0.4011. Min Range: -0.4011

Max Act: 0.3107. Min Act: -0.0000

Data Index: 677705 (C4 (Web Text))

Max Activating Token Index: 860

Text #12

Max Range: 0.4011. Min Range: -0.4011

Max Act: 0.2711. Min Act: -0.0000

Data Index: 1001075 (C4 (Web Text))

Max Activating Token Index: 978

Text #13

Max Range: 0.4011. Min Range: -0.4011

Max Act: 0.2825. Min Act: -0.0000

Data Index: 1099064 (C4 (Web Text))

Max Activating Token Index: 552

Text #14

Max Range: 0.4011. Min Range: -0.4011

Max Act: 0.3008. Min Act: -0.0000

Data Index: 1122945 (C4 (Web Text))

Max Activating Token Index: 344

Text #15

Max Range: 0.4011. Min Range: -0.4011

Max Act: 0.2799. Min Act: -0.0000

Data Index: 546131 (C4 (Web Text))

Max Activating Token Index: 233

Text #16

Max Range: 0.4011. Min Range: -0.4011

Max Act: 0.2761. Min Act: -0.0000

Data Index: 459009 (C4 (Web Text))

Max Activating Token Index: 758

Text #17

Max Range: 0.4011. Min Range: -0.4011

Max Act: 0.2853. Min Act: -0.0000

Data Index: 291746 (C4 (Web Text))

Max Activating Token Index: 636

Text #18

Max Range: 0.4011. Min Range: -0.4011

Max Act: 0.2714. Min Act: -0.0000

Data Index: 647611 (C4 (Web Text))

Max Activating Token Index: 904

Text #19

Max Range: 0.4011. Min Range: -0.4011

Max Act: 0.2851. Min Act: -0.0000

Data Index: 828644 (C4 (Web Text))

Max Activating Token Index: 261