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

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

Neuron 594 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.4033. Min Act: -0.0002

Data Index: 922006 (C4 (Web Text))

Max Activating Token Index: 850

Text #1

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.3655. Min Act: -0.0001

Data Index: 474366 (C4 (Web Text))

Max Activating Token Index: 820

Text #2

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.3508. Min Act: -0.0001

Data Index: 1160447 (C4 (Web Text))

Max Activating Token Index: 387

Text #3

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.3311. Min Act: -0.0002

Data Index: 278334 (C4 (Web Text))

Max Activating Token Index: 948

Text #4

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.3476. Min Act: -0.0001

Data Index: 539977 (C4 (Web Text))

Max Activating Token Index: 972

Text #5

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.3538. Min Act: -0.0001

Data Index: 193587 (C4 (Web Text))

Max Activating Token Index: 428

Text #6

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.3412. Min Act: -0.0002

Data Index: 1042725 (C4 (Web Text))

Max Activating Token Index: 844

Text #7

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.3508. Min Act: -0.0002

Data Index: 668446 (C4 (Web Text))

Max Activating Token Index: 765

Text #8

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.3475. Min Act: -0.0001

Data Index: 467225 (C4 (Web Text))

Max Activating Token Index: 455

Text #9

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.3816. Min Act: -0.0001

Data Index: 589341 (C4 (Web Text))

Max Activating Token Index: 721

Text #10

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.3434. Min Act: -0.0002

Data Index: 1359088 (C4 (Web Text))

Max Activating Token Index: 934

Text #11

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.3452. Min Act: -0.0002

Data Index: 377384 (C4 (Web Text))

Max Activating Token Index: 601

Text #12

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.3471. Min Act: -0.0002

Data Index: 179147 (C4 (Web Text))

Max Activating Token Index: 1009

Text #13

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.3043. Min Act: -0.0002

Data Index: 1207978 (C4 (Web Text))

Max Activating Token Index: 699

Text #14

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.3169. Min Act: -0.0002

Data Index: 817750 (C4 (Web Text))

Max Activating Token Index: 366

Text #15

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.3142. Min Act: -0.0001

Data Index: 1275154 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.3129. Min Act: -0.0002

Data Index: 647573 (C4 (Web Text))

Max Activating Token Index: 432

Text #17

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.3140. Min Act: -0.0001

Data Index: 74340 (C4 (Web Text))

Max Activating Token Index: 938

Text #18

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.3291. Min Act: -0.0001

Data Index: 348097 (C4 (Web Text))

Max Activating Token Index: 360

Text #19

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.3502. Min Act: -0.0002

Data Index: 191337 (C4 (Web Text))

Max Activating Token Index: 270