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

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

Neuron 3099 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: 0.4097. Min Range: -0.4097

Max Act: 0.4097. Min Act: -0.0001

Data Index: 379776 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.3307. Min Act: -0.0000

Data Index: 1325957 (C4 (Web Text))

Max Activating Token Index: 92

Text #2

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.3262. Min Act: -0.0000

Data Index: 1324200 (C4 (Web Text))

Max Activating Token Index: 87

Text #3

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.3183. Min Act: -0.0001

Data Index: 1351603 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.3216. Min Act: -0.0001

Data Index: 183028 (C4 (Web Text))

Max Activating Token Index: 503

Text #5

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.3111. Min Act: -0.0001

Data Index: 240224 (C4 (Web Text))

Max Activating Token Index: 815

Text #6

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2941. Min Act: -0.0001

Data Index: 405017 (C4 (Web Text))

Max Activating Token Index: 296

Text #7

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.3175. Min Act: -0.0001

Data Index: 486857 (C4 (Web Text))

Max Activating Token Index: 157

Text #8

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.3001. Min Act: -0.0001

Data Index: 106933 (C4 (Web Text))

Max Activating Token Index: 827

Text #9

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2938. Min Act: -0.0001

Data Index: 1165664 (C4 (Web Text))

Max Activating Token Index: 115

Text #10

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2946. Min Act: -0.0000

Data Index: 1153819 (C4 (Web Text))

Max Activating Token Index: 273

Text #11

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2773. Min Act: -0.0001

Data Index: 1004864 (C4 (Web Text))

Max Activating Token Index: 250

Text #12

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2842. Min Act: -0.0001

Data Index: 1286496 (C4 (Web Text))

Max Activating Token Index: 661

Text #13

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2795. Min Act: -0.0001

Data Index: 238789 (C4 (Web Text))

Max Activating Token Index: 81

Text #14

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2942. Min Act: -0.0000

Data Index: 545847 (C4 (Web Text))

Max Activating Token Index: 853

Text #15

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2609. Min Act: -0.0001

Data Index: 5496 (C4 (Web Text))

Max Activating Token Index: 697

Text #16

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2792. Min Act: -0.0001

Data Index: 475437 (C4 (Web Text))

Max Activating Token Index: 144

Text #17

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2606. Min Act: -0.0001

Data Index: 808802 (C4 (Web Text))

Max Activating Token Index: 180

Text #18

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2656. Min Act: -0.0001

Data Index: 110737 (C4 (Web Text))

Max Activating Token Index: 361

Text #19

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2745. Min Act: -0.0001

Data Index: 372658 (C4 (Web Text))

Max Activating Token Index: 978