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

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

Neuron 257 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4732. Min Range: -0.4732

Max Act: 0.4732. Min Act: -0.0001

Data Index: 1233760 (C4 (Web Text))

Max Activating Token Index: 279

Text #1

Max Range: 0.4732. Min Range: -0.4732

Max Act: 0.4289. Min Act: -0.0001

Data Index: 817240 (C4 (Web Text))

Max Activating Token Index: 422

Text #2

Max Range: 0.4732. Min Range: -0.4732

Max Act: 0.4164. Min Act: -0.0001

Data Index: 842531 (C4 (Web Text))

Max Activating Token Index: 51

Text #3

Max Range: 0.4732. Min Range: -0.4732

Max Act: 0.3884. Min Act: -0.0001

Data Index: 602040 (C4 (Web Text))

Max Activating Token Index: 660

Text #4

Max Range: 0.4732. Min Range: -0.4732

Max Act: 0.4125. Min Act: -0.0001

Data Index: 677276 (C4 (Web Text))

Max Activating Token Index: 724

Text #5

Max Range: 0.4732. Min Range: -0.4732

Max Act: 0.3803. Min Act: -0.0001

Data Index: 913632 (C4 (Web Text))

Max Activating Token Index: 199

Text #6

Max Range: 0.4732. Min Range: -0.4732

Max Act: 0.3948. Min Act: -0.0001

Data Index: 1070570 (C4 (Web Text))

Max Activating Token Index: 909

Text #7

Max Range: 0.4732. Min Range: -0.4732

Max Act: 0.3889. Min Act: -0.0001

Data Index: 961738 (C4 (Web Text))

Max Activating Token Index: 54

Text #8

Max Range: 0.4732. Min Range: -0.4732

Max Act: 0.3704. Min Act: -0.0001

Data Index: 341193 (C4 (Web Text))

Max Activating Token Index: 849

Text #9

Max Range: 0.4732. Min Range: -0.4732

Max Act: 0.3368. Min Act: -0.0001

Data Index: 78145 (C4 (Web Text))

Max Activating Token Index: 629

Text #10

Max Range: 0.4732. Min Range: -0.4732

Max Act: 0.3578. Min Act: -0.0001

Data Index: 282314 (C4 (Web Text))

Max Activating Token Index: 581

Text #11

Max Range: 0.4732. Min Range: -0.4732

Max Act: 0.3369. Min Act: -0.0001

Data Index: 297534 (C4 (Web Text))

Max Activating Token Index: 206

Text #12

Max Range: 0.4732. Min Range: -0.4732

Max Act: 0.3437. Min Act: -0.0001

Data Index: 684337 (C4 (Web Text))

Max Activating Token Index: 397

Text #13

Max Range: 0.4732. Min Range: -0.4732

Max Act: 0.3421. Min Act: -0.0001

Data Index: 468938 (C4 (Web Text))

Max Activating Token Index: 54

Text #14

Max Range: 0.4732. Min Range: -0.4732

Max Act: 0.3289. Min Act: -0.0001

Data Index: 33089 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 0.4732. Min Range: -0.4732

Max Act: 0.3294. Min Act: -0.0001

Data Index: 906885 (C4 (Web Text))

Max Activating Token Index: 604

Text #16

Max Range: 0.4732. Min Range: -0.4732

Max Act: 0.3369. Min Act: -0.0001

Data Index: 1267794 (C4 (Web Text))

Max Activating Token Index: 330

Text #17

Max Range: 0.4732. Min Range: -0.4732

Max Act: 0.3247. Min Act: -0.0001

Data Index: 338164 (C4 (Web Text))

Max Activating Token Index: 247

Text #18

Max Range: 0.4732. Min Range: -0.4732

Max Act: 0.3342. Min Act: -0.0001

Data Index: 748089 (C4 (Web Text))

Max Activating Token Index: 514

Text #19

Max Range: 0.4732. Min Range: -0.4732

Max Act: 0.3222. Min Act: -0.0001

Data Index: 478228 (C4 (Web Text))

Max Activating Token Index: 916