Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3936 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2924. Min Act: -0.0001

Data Index: 503743 (C4 (Web Text))

Max Activating Token Index: 520

Text #1

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2985. Min Act: -0.0001

Data Index: 857361 (C4 (Web Text))

Max Activating Token Index: 882

Text #2

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2859. Min Act: -0.0001

Data Index: 182905 (C4 (Web Text))

Max Activating Token Index: 595

Text #3

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.3040. Min Act: -0.0001

Data Index: 455231 (C4 (Web Text))

Max Activating Token Index: 788

Text #4

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.3016. Min Act: -0.0001

Data Index: 391815 (C4 (Web Text))

Max Activating Token Index: 284

Text #5

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2748. Min Act: -0.0001

Data Index: 575372 (C4 (Web Text))

Max Activating Token Index: 380

Text #6

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2610. Min Act: -0.0001

Data Index: 345267 (C4 (Web Text))

Max Activating Token Index: 620

Text #7

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2706. Min Act: -0.0001

Data Index: 192799 (C4 (Web Text))

Max Activating Token Index: 385

Text #8

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2704. Min Act: -0.0001

Data Index: 1187359 (C4 (Web Text))

Max Activating Token Index: 855

Text #9

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2605. Min Act: -0.0001

Data Index: 987076 (C4 (Web Text))

Max Activating Token Index: 332

Text #10

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2626. Min Act: -0.0001

Data Index: 1265661 (C4 (Web Text))

Max Activating Token Index: 957

Text #11

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2537. Min Act: -0.0001

Data Index: 725407 (C4 (Web Text))

Max Activating Token Index: 1010

Text #12

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2292. Min Act: -0.0001

Data Index: 40941 (C4 (Web Text))

Max Activating Token Index: 717

Text #13

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2481. Min Act: -0.0001

Data Index: 222699 (C4 (Web Text))

Max Activating Token Index: 442

Text #14

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2481. Min Act: -0.0001

Data Index: 642223 (C4 (Web Text))

Max Activating Token Index: 595

Text #15

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2311. Min Act: -0.0001

Data Index: 732672 (C4 (Web Text))

Max Activating Token Index: 646

Text #16

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2464. Min Act: -0.0001

Data Index: 279376 (C4 (Web Text))

Max Activating Token Index: 690

Text #17

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2454. Min Act: -0.0001

Data Index: 526419 (C4 (Web Text))

Max Activating Token Index: 774

Text #18

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2440. Min Act: -0.0000

Data Index: 445674 (C4 (Web Text))

Max Activating Token Index: 695

Text #19

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2432. Min Act: -0.0001

Data Index: 1183086 (C4 (Web Text))

Max Activating Token Index: 422