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

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

Neuron 3796 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: 0.3904. Min Range: -0.3904

Max Act: 0.3904. Min Act: -0.0001

Data Index: 279085 (C4 (Web Text))

Max Activating Token Index: 442

Text #1

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.3801. Min Act: -0.0001

Data Index: 394816 (C4 (Web Text))

Max Activating Token Index: 386

Text #2

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.3664. Min Act: -0.0001

Data Index: 541676 (C4 (Web Text))

Max Activating Token Index: 387

Text #3

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.3719. Min Act: -0.0001

Data Index: 273674 (C4 (Web Text))

Max Activating Token Index: 957

Text #4

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.3750. Min Act: -0.0001

Data Index: 410754 (C4 (Web Text))

Max Activating Token Index: 124

Text #5

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.3644. Min Act: -0.0001

Data Index: 963986 (C4 (Web Text))

Max Activating Token Index: 826

Text #6

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.3513. Min Act: -0.0001

Data Index: 783972 (C4 (Web Text))

Max Activating Token Index: 592

Text #7

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.3526. Min Act: -0.0001

Data Index: 1291555 (C4 (Web Text))

Max Activating Token Index: 563

Text #8

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.3461. Min Act: -0.0001

Data Index: 435090 (C4 (Web Text))

Max Activating Token Index: 800

Text #9

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.3496. Min Act: -0.0001

Data Index: 1044571 (C4 (Web Text))

Max Activating Token Index: 855

Text #10

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.3295. Min Act: -0.0001

Data Index: 209139 (C4 (Web Text))

Max Activating Token Index: 866

Text #11

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.3312. Min Act: -0.0001

Data Index: 1325152 (C4 (Web Text))

Max Activating Token Index: 933

Text #12

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.3285. Min Act: -0.0001

Data Index: 874242 (C4 (Web Text))

Max Activating Token Index: 445

Text #13

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.3538. Min Act: -0.0001

Data Index: 948647 (C4 (Web Text))

Max Activating Token Index: 544

Text #14

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.3497. Min Act: -0.0001

Data Index: 1200212 (C4 (Web Text))

Max Activating Token Index: 841

Text #15

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.3154. Min Act: -0.0001

Data Index: 1095580 (C4 (Web Text))

Max Activating Token Index: 104

Text #16

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.3084. Min Act: -0.0001

Data Index: 1340636 (C4 (Web Text))

Max Activating Token Index: 1017

Text #17

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.3145. Min Act: -0.0001

Data Index: 651958 (C4 (Web Text))

Max Activating Token Index: 261

Text #18

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.3166. Min Act: -0.0001

Data Index: 453286 (C4 (Web Text))

Max Activating Token Index: 68

Text #19

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.3020. Min Act: -0.0001

Data Index: 11227 (C4 (Web Text))

Max Activating Token Index: 746