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

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

Neuron 2311 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: 0.8301. Min Range: -0.8301

Max Act: 0.8301. Min Act: -0.0000

Data Index: 1047834 (C4 (Web Text))

Max Activating Token Index: 610

Text #1

Max Range: 0.8301. Min Range: -0.8301

Max Act: 0.8040. Min Act: -0.0000

Data Index: 683257 (C4 (Web Text))

Max Activating Token Index: 601

Text #2

Max Range: 0.8301. Min Range: -0.8301

Max Act: 0.6870. Min Act: -0.0000

Data Index: 913391 (C4 (Web Text))

Max Activating Token Index: 438

Text #3

Max Range: 0.8301. Min Range: -0.8301

Max Act: 0.5815. Min Act: -0.0000

Data Index: 757027 (C4 (Web Text))

Max Activating Token Index: 705

Text #4

Max Range: 0.8301. Min Range: -0.8301

Max Act: 0.5669. Min Act: -0.0000

Data Index: 943349 (C4 (Web Text))

Max Activating Token Index: 631

Text #5

Max Range: 0.8301. Min Range: -0.8301

Max Act: 0.5037. Min Act: -0.0000

Data Index: 1476789 (Python Code)

Max Activating Token Index: 804

Text #6

Max Range: 0.8301. Min Range: -0.8301

Max Act: 0.3876. Min Act: -0.0000

Data Index: 1523436 (Python Code)

Max Activating Token Index: 942

Text #7

Max Range: 0.8301. Min Range: -0.8301

Max Act: 0.3238. Min Act: -0.0000

Data Index: 958359 (C4 (Web Text))

Max Activating Token Index: 485

Text #8

Max Range: 0.8301. Min Range: -0.8301

Max Act: 0.2794. Min Act: -0.0000

Data Index: 327860 (C4 (Web Text))

Max Activating Token Index: 756

Text #9

Max Range: 0.8301. Min Range: -0.8301

Max Act: 0.2774. Min Act: -0.0000

Data Index: 1282154 (C4 (Web Text))

Max Activating Token Index: 215

Text #10

Max Range: 0.8301. Min Range: -0.8301

Max Act: 0.2966. Min Act: -0.0000

Data Index: 1229064 (C4 (Web Text))

Max Activating Token Index: 395

Text #11

Max Range: 0.8301. Min Range: -0.8301

Max Act: 0.3014. Min Act: -0.0000

Data Index: 1242741 (C4 (Web Text))

Max Activating Token Index: 215

Text #12

Max Range: 0.8301. Min Range: -0.8301

Max Act: 0.2638. Min Act: -0.0000

Data Index: 42227 (C4 (Web Text))

Max Activating Token Index: 289

Text #13

Max Range: 0.8301. Min Range: -0.8301

Max Act: 0.2790. Min Act: -0.0000

Data Index: 1515840 (Python Code)

Max Activating Token Index: 202

Text #14

Max Range: 0.8301. Min Range: -0.8301

Max Act: 0.2692. Min Act: -0.0000

Data Index: 400782 (C4 (Web Text))

Max Activating Token Index: 176

Text #15

Max Range: 0.8301. Min Range: -0.8301

Max Act: 0.2387. Min Act: -0.0000

Data Index: 348523 (C4 (Web Text))

Max Activating Token Index: 113

Text #16

Max Range: 0.8301. Min Range: -0.8301

Max Act: 0.2424. Min Act: -0.0000

Data Index: 867310 (C4 (Web Text))

Max Activating Token Index: 839

Text #17

Max Range: 0.8301. Min Range: -0.8301

Max Act: 0.2586. Min Act: -0.0000

Data Index: 1103600 (C4 (Web Text))

Max Activating Token Index: 584

Text #18

Max Range: 0.8301. Min Range: -0.8301

Max Act: 0.2457. Min Act: -0.0000

Data Index: 511124 (C4 (Web Text))

Max Activating Token Index: 815

Text #19

Max Range: 0.8301. Min Range: -0.8301

Max Act: 0.2510. Min Act: -0.0000

Data Index: 1314970 (C4 (Web Text))

Max Activating Token Index: 817