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

Dataset: The Pile

Neuron 4741 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6444. Min Range: -1.6444

Max Act: 1.6444. Min Act: -0.0000

Data Index: 517526 (The Pile)

Max Activating Token Index: 276

Text #1

Max Range: 1.6444. Min Range: -1.6444

Max Act: 1.6001. Min Act: -0.0000

Data Index: 1594935 (The Pile)

Max Activating Token Index: 1013

Text #2

Max Range: 1.6444. Min Range: -1.6444

Max Act: 1.3881. Min Act: -0.0000

Data Index: 578057 (The Pile)

Max Activating Token Index: 757

Text #3

Max Range: 1.6444. Min Range: -1.6444

Max Act: 1.4549. Min Act: -0.0000

Data Index: 938340 (The Pile)

Max Activating Token Index: 981

Text #4

Max Range: 1.6444. Min Range: -1.6444

Max Act: 1.4223. Min Act: -0.0000

Data Index: 23036 (The Pile)

Max Activating Token Index: 748

Text #5

Max Range: 1.6444. Min Range: -1.6444

Max Act: 1.4053. Min Act: -0.0000

Data Index: 882569 (The Pile)

Max Activating Token Index: 202

Text #6

Max Range: 1.6444. Min Range: -1.6444

Max Act: 1.2349. Min Act: -0.0000

Data Index: 599690 (The Pile)

Max Activating Token Index: 169

Text #7

Max Range: 1.6444. Min Range: -1.6444

Max Act: 1.3837. Min Act: -0.0000

Data Index: 548084 (The Pile)

Max Activating Token Index: 378

Text #8

Max Range: 1.6444. Min Range: -1.6444

Max Act: 1.3309. Min Act: -0.0000

Data Index: 1054225 (The Pile)

Max Activating Token Index: 448

Text #9

Max Range: 1.6444. Min Range: -1.6444

Max Act: 1.3025. Min Act: -0.0000

Data Index: 656636 (The Pile)

Max Activating Token Index: 625

Text #10

Max Range: 1.6444. Min Range: -1.6444

Max Act: 1.3649. Min Act: -0.0000

Data Index: 769973 (The Pile)

Max Activating Token Index: 887

Text #11

Max Range: 1.6444. Min Range: -1.6444

Max Act: 1.1902. Min Act: -0.0000

Data Index: 383617 (The Pile)

Max Activating Token Index: 669

Text #12

Max Range: 1.6444. Min Range: -1.6444

Max Act: 1.3257. Min Act: -0.0000

Data Index: 1758860 (The Pile)

Max Activating Token Index: 331

Text #13

Max Range: 1.6444. Min Range: -1.6444

Max Act: 1.4084. Min Act: -0.0000

Data Index: 1969658 (The Pile)

Max Activating Token Index: 35

Text #14

Max Range: 1.6444. Min Range: -1.6444

Max Act: 1.3136. Min Act: -0.0000

Data Index: 175242 (The Pile)

Max Activating Token Index: 774

Text #15

Max Range: 1.6444. Min Range: -1.6444

Max Act: 1.3988. Min Act: -0.0000

Data Index: 1216551 (The Pile)

Max Activating Token Index: 520

Text #16

Max Range: 1.6444. Min Range: -1.6444

Max Act: 1.1710. Min Act: -0.0000

Data Index: 905279 (The Pile)

Max Activating Token Index: 1004

Text #17

Max Range: 1.6444. Min Range: -1.6444

Max Act: 1.2512. Min Act: -0.0000

Data Index: 434399 (The Pile)

Max Activating Token Index: 842

Text #18

Max Range: 1.6444. Min Range: -1.6444

Max Act: 1.2791. Min Act: -0.0000

Data Index: 218201 (The Pile)

Max Activating Token Index: 809

Text #19

Max Range: 1.6444. Min Range: -1.6444

Max Act: 1.2669. Min Act: -0.0000

Data Index: 1331387 (The Pile)

Max Activating Token Index: 295