Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1664 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5936. Min Range: -0.5936

Max Act: 0.5936. Min Act: -0.0000

Data Index: 827578 (C4 (Web Text))

Max Activating Token Index: 959

Text #1

Max Range: 0.5936. Min Range: -0.5936

Max Act: 0.3833. Min Act: 0.0000

Data Index: 210419 (C4 (Web Text))

Max Activating Token Index: 970

Text #2

Max Range: 0.5936. Min Range: -0.5936

Max Act: 0.3670. Min Act: -0.0000

Data Index: 195974 (C4 (Web Text))

Max Activating Token Index: 183

Text #3

Max Range: 0.5936. Min Range: -0.5936

Max Act: 0.3373. Min Act: -0.0000

Data Index: 170248 (C4 (Web Text))

Max Activating Token Index: 205

Text #4

Max Range: 0.5936. Min Range: -0.5936

Max Act: 0.3245. Min Act: -0.0000

Data Index: 75295 (C4 (Web Text))

Max Activating Token Index: 933

Text #5

Max Range: 0.5936. Min Range: -0.5936

Max Act: 0.3286. Min Act: 0.0001

Data Index: 815505 (C4 (Web Text))

Max Activating Token Index: 763

Text #6

Max Range: 0.5936. Min Range: -0.5936

Max Act: 0.3235. Min Act: 0.0000

Data Index: 798016 (C4 (Web Text))

Max Activating Token Index: 303

Text #7

Max Range: 0.5936. Min Range: -0.5936

Max Act: 0.3074. Min Act: -0.0000

Data Index: 523830 (C4 (Web Text))

Max Activating Token Index: 321

Text #8

Max Range: 0.5936. Min Range: -0.5936

Max Act: 0.2967. Min Act: -0.0000

Data Index: 537769 (C4 (Web Text))

Max Activating Token Index: 169

Text #9

Max Range: 0.5936. Min Range: -0.5936

Max Act: 0.3046. Min Act: 0.0000

Data Index: 837131 (C4 (Web Text))

Max Activating Token Index: 454

Text #10

Max Range: 0.5936. Min Range: -0.5936

Max Act: 0.2826. Min Act: -0.0000

Data Index: 209124 (C4 (Web Text))

Max Activating Token Index: 54

Text #11

Max Range: 0.5936. Min Range: -0.5936

Max Act: 0.3003. Min Act: -0.0000

Data Index: 735723 (C4 (Web Text))

Max Activating Token Index: 629

Text #12

Max Range: 0.5936. Min Range: -0.5936

Max Act: 0.2806. Min Act: 0.0000

Data Index: 266320 (C4 (Web Text))

Max Activating Token Index: 160

Text #13

Max Range: 0.5936. Min Range: -0.5936

Max Act: 0.2808. Min Act: -0.0000

Data Index: 1172702 (C4 (Web Text))

Max Activating Token Index: 281

Text #14

Max Range: 0.5936. Min Range: -0.5936

Max Act: 0.2722. Min Act: -0.0000

Data Index: 352012 (C4 (Web Text))

Max Activating Token Index: 556

Text #15

Max Range: 0.5936. Min Range: -0.5936

Max Act: 0.2712. Min Act: -0.0000

Data Index: 176160 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 0.5936. Min Range: -0.5936

Max Act: 0.2699. Min Act: -0.0000

Data Index: 1307182 (C4 (Web Text))

Max Activating Token Index: 938

Text #17

Max Range: 0.5936. Min Range: -0.5936

Max Act: 0.2631. Min Act: -0.0000

Data Index: 1554649 (Python Code)

Max Activating Token Index: 117

Text #18

Max Range: 0.5936. Min Range: -0.5936

Max Act: 0.2754. Min Act: -0.0000

Data Index: 198843 (C4 (Web Text))

Max Activating Token Index: 876

Text #19

Max Range: 0.5936. Min Range: -0.5936

Max Act: 0.2579. Min Act: -0.0000

Data Index: 355541 (C4 (Web Text))

Max Activating Token Index: 175