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

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

Neuron 4948 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5283. Min Range: -0.5283

Max Act: 0.4586. Min Act: -0.0000

Data Index: 274002 (C4 (Web Text))

Max Activating Token Index: 111

Text #1

Max Range: 0.5283. Min Range: -0.5283

Max Act: 0.5283. Min Act: -0.0000

Data Index: 53951 (C4 (Web Text))

Max Activating Token Index: 408

Text #2

Max Range: 0.5283. Min Range: -0.5283

Max Act: 0.4058. Min Act: -0.0000

Data Index: 717746 (C4 (Web Text))

Max Activating Token Index: 579

Text #3

Max Range: 0.5283. Min Range: -0.5283

Max Act: 0.3992. Min Act: -0.0000

Data Index: 1340409 (C4 (Web Text))

Max Activating Token Index: 361

Text #4

Max Range: 0.5283. Min Range: -0.5283

Max Act: 0.3721. Min Act: -0.0000

Data Index: 216440 (C4 (Web Text))

Max Activating Token Index: 954

Text #5

Max Range: 0.5283. Min Range: -0.5283

Max Act: 0.3668. Min Act: -0.0000

Data Index: 644044 (C4 (Web Text))

Max Activating Token Index: 611

Text #6

Max Range: 0.5283. Min Range: -0.5283

Max Act: 0.3631. Min Act: -0.0000

Data Index: 1247016 (C4 (Web Text))

Max Activating Token Index: 702

Text #7

Max Range: 0.5283. Min Range: -0.5283

Max Act: 0.3700. Min Act: -0.0000

Data Index: 561754 (C4 (Web Text))

Max Activating Token Index: 544

Text #8

Max Range: 0.5283. Min Range: -0.5283

Max Act: 0.3742. Min Act: -0.0000

Data Index: 957162 (C4 (Web Text))

Max Activating Token Index: 575

Text #9

Max Range: 0.5283. Min Range: -0.5283

Max Act: 0.3476. Min Act: -0.0000

Data Index: 43119 (C4 (Web Text))

Max Activating Token Index: 5

Text #10

Max Range: 0.5283. Min Range: -0.5283

Max Act: 0.3686. Min Act: -0.0000

Data Index: 313504 (C4 (Web Text))

Max Activating Token Index: 566

Text #11

Max Range: 0.5283. Min Range: -0.5283

Max Act: 0.3414. Min Act: -0.0000

Data Index: 567351 (C4 (Web Text))

Max Activating Token Index: 708

Text #12

Max Range: 0.5283. Min Range: -0.5283

Max Act: 0.3438. Min Act: -0.0000

Data Index: 742056 (C4 (Web Text))

Max Activating Token Index: 716

Text #13

Max Range: 0.5283. Min Range: -0.5283

Max Act: 0.3333. Min Act: -0.0000

Data Index: 153261 (C4 (Web Text))

Max Activating Token Index: 856

Text #14

Max Range: 0.5283. Min Range: -0.5283

Max Act: 0.3518. Min Act: -0.0000

Data Index: 638106 (C4 (Web Text))

Max Activating Token Index: 363

Text #15

Max Range: 0.5283. Min Range: -0.5283

Max Act: 0.3349. Min Act: -0.0000

Data Index: 1247306 (C4 (Web Text))

Max Activating Token Index: 71

Text #16

Max Range: 0.5283. Min Range: -0.5283

Max Act: 0.3272. Min Act: -0.0000

Data Index: 1163376 (C4 (Web Text))

Max Activating Token Index: 157

Text #17

Max Range: 0.5283. Min Range: -0.5283

Max Act: 0.2967. Min Act: -0.0000

Data Index: 1197142 (C4 (Web Text))

Max Activating Token Index: 828

Text #18

Max Range: 0.5283. Min Range: -0.5283

Max Act: 0.3128. Min Act: -0.0000

Data Index: 1040115 (C4 (Web Text))

Max Activating Token Index: 900

Text #19

Max Range: 0.5283. Min Range: -0.5283

Max Act: 0.2943. Min Act: -0.0000

Data Index: 131316 (C4 (Web Text))

Max Activating Token Index: 509