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

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

Neuron 5122 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.4346. Min Act: -0.0002

Data Index: 989670 (C4 (Web Text))

Max Activating Token Index: 636

Text #1

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.4636. Min Act: -0.0002

Data Index: 82755 (C4 (Web Text))

Max Activating Token Index: 718

Text #2

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.3341. Min Act: -0.0002

Data Index: 1305960 (C4 (Web Text))

Max Activating Token Index: 580

Text #3

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.3111. Min Act: -0.0002

Data Index: 473573 (C4 (Web Text))

Max Activating Token Index: 270

Text #4

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.2723. Min Act: -0.0002

Data Index: 870811 (C4 (Web Text))

Max Activating Token Index: 617

Text #5

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.2854. Min Act: -0.0002

Data Index: 1312257 (C4 (Web Text))

Max Activating Token Index: 396

Text #6

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.2752. Min Act: -0.0002

Data Index: 1320029 (C4 (Web Text))

Max Activating Token Index: 308

Text #7

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.3061. Min Act: -0.0002

Data Index: 966751 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.2686. Min Act: -0.0002

Data Index: 944495 (C4 (Web Text))

Max Activating Token Index: 560

Text #9

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.2482. Min Act: -0.0002

Data Index: 966180 (C4 (Web Text))

Max Activating Token Index: 865

Text #10

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.2573. Min Act: -0.0002

Data Index: 957094 (C4 (Web Text))

Max Activating Token Index: 648

Text #11

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.2352. Min Act: -0.0002

Data Index: 135325 (C4 (Web Text))

Max Activating Token Index: 167

Text #12

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.2728. Min Act: -0.0002

Data Index: 1003708 (C4 (Web Text))

Max Activating Token Index: 69

Text #13

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.2232. Min Act: -0.0002

Data Index: 858696 (C4 (Web Text))

Max Activating Token Index: 696

Text #14

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.2027. Min Act: -0.0002

Data Index: 280484 (C4 (Web Text))

Max Activating Token Index: 754

Text #15

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.2282. Min Act: -0.0002

Data Index: 857016 (C4 (Web Text))

Max Activating Token Index: 762

Text #16

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.1846. Min Act: -0.0002

Data Index: 984992 (C4 (Web Text))

Max Activating Token Index: 433

Text #17

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.2332. Min Act: -0.0002

Data Index: 727054 (C4 (Web Text))

Max Activating Token Index: 170

Text #18

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.1890. Min Act: -0.0002

Data Index: 579886 (C4 (Web Text))

Max Activating Token Index: 269

Text #19

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.2130. Min Act: -0.0002

Data Index: 461037 (C4 (Web Text))

Max Activating Token Index: 255