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

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

Neuron 3874 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: 0.3262. Min Range: -0.3262

Max Act: 0.3262. Min Act: -0.0000

Data Index: 792664 (C4 (Web Text))

Max Activating Token Index: 103

Text #1

Max Range: 0.3262. Min Range: -0.3262

Max Act: 0.3033. Min Act: -0.0000

Data Index: 1161224 (C4 (Web Text))

Max Activating Token Index: 134

Text #2

Max Range: 0.3262. Min Range: -0.3262

Max Act: 0.2983. Min Act: -0.0001

Data Index: 134034 (C4 (Web Text))

Max Activating Token Index: 183

Text #3

Max Range: 0.3262. Min Range: -0.3262

Max Act: 0.2840. Min Act: -0.0001

Data Index: 1133119 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 0.3262. Min Range: -0.3262

Max Act: 0.2940. Min Act: -0.0000

Data Index: 805292 (C4 (Web Text))

Max Activating Token Index: 269

Text #5

Max Range: 0.3262. Min Range: -0.3262

Max Act: 0.2840. Min Act: -0.0001

Data Index: 1110454 (C4 (Web Text))

Max Activating Token Index: 359

Text #6

Max Range: 0.3262. Min Range: -0.3262

Max Act: 0.3014. Min Act: -0.0000

Data Index: 261397 (C4 (Web Text))

Max Activating Token Index: 536

Text #7

Max Range: 0.3262. Min Range: -0.3262

Max Act: 0.2968. Min Act: -0.0001

Data Index: 329001 (C4 (Web Text))

Max Activating Token Index: 208

Text #8

Max Range: 0.3262. Min Range: -0.3262

Max Act: 0.2865. Min Act: -0.0000

Data Index: 321831 (C4 (Web Text))

Max Activating Token Index: 197

Text #9

Max Range: 0.3262. Min Range: -0.3262

Max Act: 0.2859. Min Act: -0.0000

Data Index: 547072 (C4 (Web Text))

Max Activating Token Index: 399

Text #10

Max Range: 0.3262. Min Range: -0.3262

Max Act: 0.2765. Min Act: -0.0000

Data Index: 1097118 (C4 (Web Text))

Max Activating Token Index: 509

Text #11

Max Range: 0.3262. Min Range: -0.3262

Max Act: 0.2833. Min Act: -0.0001

Data Index: 1282097 (C4 (Web Text))

Max Activating Token Index: 544

Text #12

Max Range: 0.3262. Min Range: -0.3262

Max Act: 0.2852. Min Act: -0.0000

Data Index: 225115 (C4 (Web Text))

Max Activating Token Index: 338

Text #13

Max Range: 0.3262. Min Range: -0.3262

Max Act: 0.2827. Min Act: -0.0001

Data Index: 523070 (C4 (Web Text))

Max Activating Token Index: 600

Text #14

Max Range: 0.3262. Min Range: -0.3262

Max Act: 0.2850. Min Act: -0.0000

Data Index: 901759 (C4 (Web Text))

Max Activating Token Index: 595

Text #15

Max Range: 0.3262. Min Range: -0.3262

Max Act: 0.2826. Min Act: -0.0001

Data Index: 142172 (C4 (Web Text))

Max Activating Token Index: 317

Text #16

Max Range: 0.3262. Min Range: -0.3262

Max Act: 0.2937. Min Act: -0.0001

Data Index: 1061157 (C4 (Web Text))

Max Activating Token Index: 391

Text #17

Max Range: 0.3262. Min Range: -0.3262

Max Act: 0.2820. Min Act: -0.0000

Data Index: 50527 (C4 (Web Text))

Max Activating Token Index: 568

Text #18

Max Range: 0.3262. Min Range: -0.3262

Max Act: 0.2974. Min Act: -0.0001

Data Index: 199644 (C4 (Web Text))

Max Activating Token Index: 252

Text #19

Max Range: 0.3262. Min Range: -0.3262

Max Act: 0.2772. Min Act: -0.0001

Data Index: 292323 (C4 (Web Text))

Max Activating Token Index: 513