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

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

Neuron 3357 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0435. Min Act: -0.0002

Data Index: 474686 (C4 (Web Text))

Max Activating Token Index: 105

Text #1

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0364. Min Act: -0.0002

Data Index: 1004075 (C4 (Web Text))

Max Activating Token Index: 298

Text #2

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0329. Min Act: -0.0002

Data Index: 295208 (C4 (Web Text))

Max Activating Token Index: 163

Text #3

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0303. Min Act: -0.0002

Data Index: 866709 (C4 (Web Text))

Max Activating Token Index: 175

Text #4

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0307. Min Act: -0.0002

Data Index: 218873 (C4 (Web Text))

Max Activating Token Index: 174

Text #5

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0328. Min Act: -0.0002

Data Index: 367284 (C4 (Web Text))

Max Activating Token Index: 264

Text #6

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0305. Min Act: -0.0002

Data Index: 824384 (C4 (Web Text))

Max Activating Token Index: 693

Text #7

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0317. Min Act: -0.0002

Data Index: 6862 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0298. Min Act: -0.0002

Data Index: 832539 (C4 (Web Text))

Max Activating Token Index: 150

Text #9

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0288. Min Act: -0.0002

Data Index: 523440 (C4 (Web Text))

Max Activating Token Index: 249

Text #10

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0305. Min Act: -0.0002

Data Index: 52412 (C4 (Web Text))

Max Activating Token Index: 34

Text #11

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0320. Min Act: -0.0002

Data Index: 141717 (C4 (Web Text))

Max Activating Token Index: 443

Text #12

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0308. Min Act: -0.0002

Data Index: 419707 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0300. Min Act: -0.0002

Data Index: 24864 (C4 (Web Text))

Max Activating Token Index: 231

Text #14

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0321. Min Act: -0.0002

Data Index: 483363 (C4 (Web Text))

Max Activating Token Index: 688

Text #15

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0297. Min Act: -0.0002

Data Index: 149803 (C4 (Web Text))

Max Activating Token Index: 524

Text #16

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0299. Min Act: -0.0002

Data Index: 699004 (C4 (Web Text))

Max Activating Token Index: 105

Text #17

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0288. Min Act: -0.0002

Data Index: 1194519 (C4 (Web Text))

Max Activating Token Index: 652

Text #18

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0302. Min Act: -0.0002

Data Index: 395661 (C4 (Web Text))

Max Activating Token Index: 473

Text #19

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0293. Min Act: -0.0002

Data Index: 412926 (C4 (Web Text))

Max Activating Token Index: 250