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

Dataset: The Pile

Neuron 2960 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4010. Min Range: -0.4010

Max Act: 0.4010. Min Act: -0.0000

Data Index: 265716 (The Pile)

Max Activating Token Index: 805

Text #1

Max Range: 0.4010. Min Range: -0.4010

Max Act: 0.3098. Min Act: -0.0000

Data Index: 780716 (The Pile)

Max Activating Token Index: 883

Text #2

Max Range: 0.4010. Min Range: -0.4010

Max Act: 0.3130. Min Act: -0.0000

Data Index: 1384653 (The Pile)

Max Activating Token Index: 114

Text #3

Max Range: 0.4010. Min Range: -0.4010

Max Act: 0.3312. Min Act: -0.0000

Data Index: 1344828 (The Pile)

Max Activating Token Index: 442

Text #4

Max Range: 0.4010. Min Range: -0.4010

Max Act: 0.3256. Min Act: -0.0000

Data Index: 176221 (The Pile)

Max Activating Token Index: 200

Text #5

Max Range: 0.4010. Min Range: -0.4010

Max Act: 0.2846. Min Act: -0.0000

Data Index: 1444211 (The Pile)

Max Activating Token Index: 302

Text #6

Max Range: 0.4010. Min Range: -0.4010

Max Act: 0.2863. Min Act: -0.0000

Data Index: 319297 (The Pile)

Max Activating Token Index: 663

Text #7

Max Range: 0.4010. Min Range: -0.4010

Max Act: 0.2466. Min Act: -0.0000

Data Index: 920913 (The Pile)

Max Activating Token Index: 863

Text #8

Max Range: 0.4010. Min Range: -0.4010

Max Act: 0.2636. Min Act: -0.0000

Data Index: 916618 (The Pile)

Max Activating Token Index: 694

Text #9

Max Range: 0.4010. Min Range: -0.4010

Max Act: 0.2874. Min Act: -0.0000

Data Index: 989160 (The Pile)

Max Activating Token Index: 517

Text #10

Max Range: 0.4010. Min Range: -0.4010

Max Act: 0.2775. Min Act: -0.0000

Data Index: 509109 (The Pile)

Max Activating Token Index: 796

Text #11

Max Range: 0.4010. Min Range: -0.4010

Max Act: 0.2834. Min Act: -0.0000

Data Index: 749745 (The Pile)

Max Activating Token Index: 328

Text #12

Max Range: 0.4010. Min Range: -0.4010

Max Act: 0.2701. Min Act: -0.0000

Data Index: 448005 (The Pile)

Max Activating Token Index: 669

Text #13

Max Range: 0.4010. Min Range: -0.4010

Max Act: 0.2664. Min Act: -0.0000

Data Index: 892550 (The Pile)

Max Activating Token Index: 903

Text #14

Max Range: 0.4010. Min Range: -0.4010

Max Act: 0.2574. Min Act: -0.0000

Data Index: 760947 (The Pile)

Max Activating Token Index: 324

Text #15

Max Range: 0.4010. Min Range: -0.4010

Max Act: 0.2658. Min Act: -0.0000

Data Index: 1744729 (The Pile)

Max Activating Token Index: 15

Text #16

Max Range: 0.4010. Min Range: -0.4010

Max Act: 0.2615. Min Act: 0.0000

Data Index: 1632888 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.4010. Min Range: -0.4010

Max Act: 0.2476. Min Act: -0.0000

Data Index: 1449514 (The Pile)

Max Activating Token Index: 261

Text #18

Max Range: 0.4010. Min Range: -0.4010

Max Act: 0.2570. Min Act: -0.0000

Data Index: 1042508 (The Pile)

Max Activating Token Index: 544

Text #19

Max Range: 0.4010. Min Range: -0.4010

Max Act: 0.2464. Min Act: -0.0000

Data Index: 1041910 (The Pile)

Max Activating Token Index: 395