Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5211 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.4010. Min Range: -5.4010

Max Act: 5.4010. Min Act: -0.0000

Data Index: 205705 (C4 (Web Text))

Max Activating Token Index: 103

Text #1

Max Range: 5.4010. Min Range: -5.4010

Max Act: 4.8165. Min Act: -0.0000

Data Index: 199735 (C4 (Web Text))

Max Activating Token Index: 749

Text #2

Max Range: 5.4010. Min Range: -5.4010

Max Act: 4.4574. Min Act: -0.0000

Data Index: 405610 (C4 (Web Text))

Max Activating Token Index: 493

Text #3

Max Range: 5.4010. Min Range: -5.4010

Max Act: 4.0920. Min Act: -0.0000

Data Index: 739713 (C4 (Web Text))

Max Activating Token Index: 203

Text #4

Max Range: 5.4010. Min Range: -5.4010

Max Act: 4.0478. Min Act: -0.0000

Data Index: 413232 (C4 (Web Text))

Max Activating Token Index: 915

Text #5

Max Range: 5.4010. Min Range: -5.4010

Max Act: 3.6277. Min Act: -0.0000

Data Index: 960593 (C4 (Web Text))

Max Activating Token Index: 785

Text #6

Max Range: 5.4010. Min Range: -5.4010

Max Act: 3.7499. Min Act: -0.0000

Data Index: 1010472 (C4 (Web Text))

Max Activating Token Index: 986

Text #7

Max Range: 5.4010. Min Range: -5.4010

Max Act: 3.7307. Min Act: -0.0000

Data Index: 664866 (C4 (Web Text))

Max Activating Token Index: 250

Text #8

Max Range: 5.4010. Min Range: -5.4010

Max Act: 3.7141. Min Act: -0.0000

Data Index: 139438 (C4 (Web Text))

Max Activating Token Index: 134

Text #9

Max Range: 5.4010. Min Range: -5.4010

Max Act: 3.7901. Min Act: -0.0000

Data Index: 1229110 (C4 (Web Text))

Max Activating Token Index: 214

Text #10

Max Range: 5.4010. Min Range: -5.4010

Max Act: 3.7257. Min Act: -0.0000

Data Index: 51892 (C4 (Web Text))

Max Activating Token Index: 816

Text #11

Max Range: 5.4010. Min Range: -5.4010

Max Act: 3.2931. Min Act: -0.0000

Data Index: 1174114 (C4 (Web Text))

Max Activating Token Index: 485

Text #12

Max Range: 5.4010. Min Range: -5.4010

Max Act: 3.3563. Min Act: -0.0000

Data Index: 1078427 (C4 (Web Text))

Max Activating Token Index: 507

Text #13

Max Range: 5.4010. Min Range: -5.4010

Max Act: 3.3760. Min Act: -0.0000

Data Index: 95923 (C4 (Web Text))

Max Activating Token Index: 493

Text #14

Max Range: 5.4010. Min Range: -5.4010

Max Act: 3.2329. Min Act: -0.0000

Data Index: 526905 (C4 (Web Text))

Max Activating Token Index: 811

Text #15

Max Range: 5.4010. Min Range: -5.4010

Max Act: 3.2771. Min Act: -0.0000

Data Index: 480723 (C4 (Web Text))

Max Activating Token Index: 347

Text #16

Max Range: 5.4010. Min Range: -5.4010

Max Act: 3.3789. Min Act: -0.0000

Data Index: 334235 (C4 (Web Text))

Max Activating Token Index: 307

Text #17

Max Range: 5.4010. Min Range: -5.4010

Max Act: 3.5805. Min Act: -0.0000

Data Index: 1102658 (C4 (Web Text))

Max Activating Token Index: 807

Text #18

Max Range: 5.4010. Min Range: -5.4010

Max Act: 3.0073. Min Act: -0.0000

Data Index: 91393 (C4 (Web Text))

Max Activating Token Index: 551

Text #19

Max Range: 5.4010. Min Range: -5.4010

Max Act: 2.9523. Min Act: -0.0000

Data Index: 1130111 (C4 (Web Text))

Max Activating Token Index: 678