Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1911 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.3786. Min Range: -4.3786

Max Act: 4.3786. Min Act: -0.0000

Data Index: 95659 (C4 (Web Text))

Max Activating Token Index: 353

Text #1

Max Range: 4.3786. Min Range: -4.3786

Max Act: 4.2456. Min Act: -0.0000

Data Index: 1835 (C4 (Web Text))

Max Activating Token Index: 879

Text #2

Max Range: 4.3786. Min Range: -4.3786

Max Act: 3.9592. Min Act: -0.0000

Data Index: 791841 (C4 (Web Text))

Max Activating Token Index: 797

Text #3

Max Range: 4.3786. Min Range: -4.3786

Max Act: 3.5835. Min Act: -0.0000

Data Index: 1259000 (C4 (Web Text))

Max Activating Token Index: 168

Text #4

Max Range: 4.3786. Min Range: -4.3786

Max Act: 3.8750. Min Act: -0.0000

Data Index: 133592 (C4 (Web Text))

Max Activating Token Index: 43

Text #5

Max Range: 4.3786. Min Range: -4.3786

Max Act: 3.8432. Min Act: -0.0000

Data Index: 789017 (C4 (Web Text))

Max Activating Token Index: 421

Text #6

Max Range: 4.3786. Min Range: -4.3786

Max Act: 3.4873. Min Act: -0.0000

Data Index: 276642 (C4 (Web Text))

Max Activating Token Index: 956

Text #7

Max Range: 4.3786. Min Range: -4.3786

Max Act: 3.5600. Min Act: -0.0000

Data Index: 1318284 (C4 (Web Text))

Max Activating Token Index: 760

Text #8

Max Range: 4.3786. Min Range: -4.3786

Max Act: 3.5062. Min Act: -0.0000

Data Index: 126986 (C4 (Web Text))

Max Activating Token Index: 995

Text #9

Max Range: 4.3786. Min Range: -4.3786

Max Act: 3.1722. Min Act: -0.0000

Data Index: 409335 (C4 (Web Text))

Max Activating Token Index: 426

Text #10

Max Range: 4.3786. Min Range: -4.3786

Max Act: 3.1424. Min Act: -0.0000

Data Index: 764777 (C4 (Web Text))

Max Activating Token Index: 705

Text #11

Max Range: 4.3786. Min Range: -4.3786

Max Act: 2.5273. Min Act: -0.0000

Data Index: 246454 (C4 (Web Text))

Max Activating Token Index: 231

Text #12

Max Range: 4.3786. Min Range: -4.3786

Max Act: 2.8579. Min Act: -0.0000

Data Index: 260626 (C4 (Web Text))

Max Activating Token Index: 47

Text #13

Max Range: 4.3786. Min Range: -4.3786

Max Act: 2.7271. Min Act: -0.0000

Data Index: 190598 (C4 (Web Text))

Max Activating Token Index: 751

Text #14

Max Range: 4.3786. Min Range: -4.3786

Max Act: 2.7779. Min Act: -0.0000

Data Index: 1043329 (C4 (Web Text))

Max Activating Token Index: 275

Text #15

Max Range: 4.3786. Min Range: -4.3786

Max Act: 2.7031. Min Act: -0.0000

Data Index: 147321 (C4 (Web Text))

Max Activating Token Index: 242

Text #16

Max Range: 4.3786. Min Range: -4.3786

Max Act: 2.7691. Min Act: -0.0000

Data Index: 861168 (C4 (Web Text))

Max Activating Token Index: 408

Text #17

Max Range: 4.3786. Min Range: -4.3786

Max Act: 2.6163. Min Act: -0.0000

Data Index: 638726 (C4 (Web Text))

Max Activating Token Index: 756

Text #18

Max Range: 4.3786. Min Range: -4.3786

Max Act: 2.6008. Min Act: -0.0000

Data Index: 656839 (C4 (Web Text))

Max Activating Token Index: 59

Text #19

Max Range: 4.3786. Min Range: -4.3786

Max Act: 2.7335. Min Act: -0.0000

Data Index: 1006056 (C4 (Web Text))

Max Activating Token Index: 100