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

Dataset: The Pile

Neuron 1352 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7516. Min Range: -3.7516

Max Act: 3.5261. Min Act: -0.0000

Data Index: 334149 (The Pile)

Max Activating Token Index: 694

Text #1

Max Range: 3.7516. Min Range: -3.7516

Max Act: 3.7516. Min Act: -0.0000

Data Index: 1594261 (The Pile)

Max Activating Token Index: 826

Text #2

Max Range: 3.7516. Min Range: -3.7516

Max Act: 3.5240. Min Act: -0.0000

Data Index: 1450377 (The Pile)

Max Activating Token Index: 248

Text #3

Max Range: 3.7516. Min Range: -3.7516

Max Act: 3.0663. Min Act: -0.0000

Data Index: 1701685 (The Pile)

Max Activating Token Index: 529

Text #4

Max Range: 3.7516. Min Range: -3.7516

Max Act: 3.2923. Min Act: -0.0000

Data Index: 579512 (The Pile)

Max Activating Token Index: 524

Text #5

Max Range: 3.7516. Min Range: -3.7516

Max Act: 3.2101. Min Act: -0.0000

Data Index: 1568689 (The Pile)

Max Activating Token Index: 417

Text #6

Max Range: 3.7516. Min Range: -3.7516

Max Act: 3.1944. Min Act: -0.0000

Data Index: 384127 (The Pile)

Max Activating Token Index: 675

Text #7

Max Range: 3.7516. Min Range: -3.7516

Max Act: 2.8816. Min Act: -0.0000

Data Index: 1047948 (The Pile)

Max Activating Token Index: 815

Text #8

Max Range: 3.7516. Min Range: -3.7516

Max Act: 3.1337. Min Act: -0.0000

Data Index: 1232733 (The Pile)

Max Activating Token Index: 852

Text #9

Max Range: 3.7516. Min Range: -3.7516

Max Act: 2.8915. Min Act: -0.0000

Data Index: 1863571 (The Pile)

Max Activating Token Index: 445

Text #10

Max Range: 3.7516. Min Range: -3.7516

Max Act: 2.3259. Min Act: -0.0000

Data Index: 138959 (The Pile)

Max Activating Token Index: 465

Text #11

Max Range: 3.7516. Min Range: -3.7516

Max Act: 2.7020. Min Act: -0.0000

Data Index: 842340 (The Pile)

Max Activating Token Index: 700

Text #12

Max Range: 3.7516. Min Range: -3.7516

Max Act: 2.8253. Min Act: -0.0000

Data Index: 250445 (The Pile)

Max Activating Token Index: 40

Text #13

Max Range: 3.7516. Min Range: -3.7516

Max Act: 2.5371. Min Act: -0.0000

Data Index: 1308537 (The Pile)

Max Activating Token Index: 101

Text #14

Max Range: 3.7516. Min Range: -3.7516

Max Act: 2.8041. Min Act: -0.0000

Data Index: 94065 (The Pile)

Max Activating Token Index: 276

Text #15

Max Range: 3.7516. Min Range: -3.7516

Max Act: 2.2436. Min Act: -0.0000

Data Index: 147868 (The Pile)

Max Activating Token Index: 549

Text #16

Max Range: 3.7516. Min Range: -3.7516

Max Act: 2.7434. Min Act: -0.0000

Data Index: 1768094 (The Pile)

Max Activating Token Index: 765

Text #17

Max Range: 3.7516. Min Range: -3.7516

Max Act: 2.3451. Min Act: -0.0000

Data Index: 289413 (The Pile)

Max Activating Token Index: 842

Text #18

Max Range: 3.7516. Min Range: -3.7516

Max Act: 3.1133. Min Act: -0.0000

Data Index: 1614559 (The Pile)

Max Activating Token Index: 155

Text #19

Max Range: 3.7516. Min Range: -3.7516

Max Act: 2.5614. Min Act: -0.0000

Data Index: 541689 (The Pile)

Max Activating Token Index: 686