Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2776 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.3745. Min Act: -0.0001

Data Index: 1115013 (C4 (Web Text))

Max Activating Token Index: 379

Text #1

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.3257. Min Act: -0.0001

Data Index: 364011 (C4 (Web Text))

Max Activating Token Index: 339

Text #2

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.3314. Min Act: -0.0001

Data Index: 1053383 (C4 (Web Text))

Max Activating Token Index: 265

Text #3

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.3029. Min Act: -0.0001

Data Index: 841222 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2965. Min Act: -0.0001

Data Index: 668601 (C4 (Web Text))

Max Activating Token Index: 493

Text #5

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.3013. Min Act: -0.0001

Data Index: 579161 (C4 (Web Text))

Max Activating Token Index: 437

Text #6

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2942. Min Act: -0.0001

Data Index: 1154559 (C4 (Web Text))

Max Activating Token Index: 947

Text #7

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2934. Min Act: -0.0001

Data Index: 18534 (C4 (Web Text))

Max Activating Token Index: 667

Text #8

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2825. Min Act: -0.0001

Data Index: 991263 (C4 (Web Text))

Max Activating Token Index: 861

Text #9

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.3006. Min Act: -0.0001

Data Index: 490918 (C4 (Web Text))

Max Activating Token Index: 641

Text #10

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2730. Min Act: -0.0001

Data Index: 889971 (C4 (Web Text))

Max Activating Token Index: 334

Text #11

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2816. Min Act: -0.0001

Data Index: 435534 (C4 (Web Text))

Max Activating Token Index: 391

Text #12

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2796. Min Act: -0.0001

Data Index: 745938 (C4 (Web Text))

Max Activating Token Index: 385

Text #13

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2766. Min Act: -0.0001

Data Index: 295729 (C4 (Web Text))

Max Activating Token Index: 534

Text #14

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2553. Min Act: -0.0001

Data Index: 394037 (C4 (Web Text))

Max Activating Token Index: 248

Text #15

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2570. Min Act: -0.0001

Data Index: 807457 (C4 (Web Text))

Max Activating Token Index: 595

Text #16

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2381. Min Act: -0.0001

Data Index: 517115 (C4 (Web Text))

Max Activating Token Index: 886

Text #17

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2462. Min Act: -0.0001

Data Index: 782377 (C4 (Web Text))

Max Activating Token Index: 248

Text #18

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2464. Min Act: -0.0001

Data Index: 1242672 (C4 (Web Text))

Max Activating Token Index: 676

Text #19

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2336. Min Act: -0.0001

Data Index: 1186957 (C4 (Web Text))

Max Activating Token Index: 286