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

Dataset: The Pile

Neuron 3808 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: 3.4857. Min Range: -3.4857

Max Act: 3.4857. Min Act: -0.0000

Data Index: 518037 (The Pile)

Max Activating Token Index: 645

Text #1

Max Range: 3.4857. Min Range: -3.4857

Max Act: 3.2945. Min Act: -0.0000

Data Index: 507199 (The Pile)

Max Activating Token Index: 383

Text #2

Max Range: 3.4857. Min Range: -3.4857

Max Act: 3.0326. Min Act: -0.0000

Data Index: 192365 (The Pile)

Max Activating Token Index: 203

Text #3

Max Range: 3.4857. Min Range: -3.4857

Max Act: 3.1224. Min Act: -0.0000

Data Index: 781855 (The Pile)

Max Activating Token Index: 363

Text #4

Max Range: 3.4857. Min Range: -3.4857

Max Act: 3.1182. Min Act: -0.0000

Data Index: 733355 (The Pile)

Max Activating Token Index: 79

Text #5

Max Range: 3.4857. Min Range: -3.4857

Max Act: 3.1948. Min Act: -0.0000

Data Index: 1854681 (The Pile)

Max Activating Token Index: 124

Text #6

Max Range: 3.4857. Min Range: -3.4857

Max Act: 2.8978. Min Act: -0.0000

Data Index: 1336475 (The Pile)

Max Activating Token Index: 138

Text #7

Max Range: 3.4857. Min Range: -3.4857

Max Act: 3.0199. Min Act: -0.0000

Data Index: 1472722 (The Pile)

Max Activating Token Index: 13

Text #8

Max Range: 3.4857. Min Range: -3.4857

Max Act: 2.9821. Min Act: -0.0000

Data Index: 326778 (The Pile)

Max Activating Token Index: 161

Text #9

Max Range: 3.4857. Min Range: -3.4857

Max Act: 2.9834. Min Act: -0.0000

Data Index: 1511332 (The Pile)

Max Activating Token Index: 537

Text #10

Max Range: 3.4857. Min Range: -3.4857

Max Act: 3.0869. Min Act: -0.0000

Data Index: 1386901 (The Pile)

Max Activating Token Index: 40

Text #11

Max Range: 3.4857. Min Range: -3.4857

Max Act: 2.9234. Min Act: -0.0000

Data Index: 1924837 (The Pile)

Max Activating Token Index: 69

Text #12

Max Range: 3.4857. Min Range: -3.4857

Max Act: 3.0358. Min Act: -0.0000

Data Index: 1235292 (The Pile)

Max Activating Token Index: 153

Text #13

Max Range: 3.4857. Min Range: -3.4857

Max Act: 2.9004. Min Act: -0.0000

Data Index: 164029 (The Pile)

Max Activating Token Index: 352

Text #14

Max Range: 3.4857. Min Range: -3.4857

Max Act: 2.7735. Min Act: -0.0000

Data Index: 193680 (The Pile)

Max Activating Token Index: 27

Text #15

Max Range: 3.4857. Min Range: -3.4857

Max Act: 2.8884. Min Act: -0.0000

Data Index: 1609389 (The Pile)

Max Activating Token Index: 110

Text #16

Max Range: 3.4857. Min Range: -3.4857

Max Act: 2.8872. Min Act: -0.0000

Data Index: 1783400 (The Pile)

Max Activating Token Index: 107

Text #17

Max Range: 3.4857. Min Range: -3.4857

Max Act: 2.8897. Min Act: -0.0000

Data Index: 1126200 (The Pile)

Max Activating Token Index: 107

Text #18

Max Range: 3.4857. Min Range: -3.4857

Max Act: 2.7337. Min Act: -0.0000

Data Index: 1880920 (The Pile)

Max Activating Token Index: 250

Text #19

Max Range: 3.4857. Min Range: -3.4857

Max Act: 2.8535. Min Act: -0.0000

Data Index: 668820 (The Pile)

Max Activating Token Index: 78