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

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

Neuron 3441 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.3538. Min Act: -0.0001

Data Index: 647688 (C4 (Web Text))

Max Activating Token Index: 555

Text #1

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.3045. Min Act: -0.0001

Data Index: 1053862 (C4 (Web Text))

Max Activating Token Index: 458

Text #2

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.2875. Min Act: -0.0001

Data Index: 89011 (C4 (Web Text))

Max Activating Token Index: 231

Text #3

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.3009. Min Act: -0.0001

Data Index: 849089 (C4 (Web Text))

Max Activating Token Index: 491

Text #4

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.2965. Min Act: -0.0001

Data Index: 993323 (C4 (Web Text))

Max Activating Token Index: 934

Text #5

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.3178. Min Act: -0.0001

Data Index: 895193 (C4 (Web Text))

Max Activating Token Index: 268

Text #6

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.2918. Min Act: -0.0001

Data Index: 1154230 (C4 (Web Text))

Max Activating Token Index: 542

Text #7

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.2798. Min Act: -0.0001

Data Index: 1300696 (C4 (Web Text))

Max Activating Token Index: 213

Text #8

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.3176. Min Act: -0.0001

Data Index: 1028217 (C4 (Web Text))

Max Activating Token Index: 81

Text #9

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.2892. Min Act: -0.0001

Data Index: 164563 (C4 (Web Text))

Max Activating Token Index: 54

Text #10

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.2996. Min Act: -0.0001

Data Index: 820510 (C4 (Web Text))

Max Activating Token Index: 455

Text #11

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.2928. Min Act: -0.0001

Data Index: 88978 (C4 (Web Text))

Max Activating Token Index: 69

Text #12

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.2749. Min Act: -0.0001

Data Index: 113547 (C4 (Web Text))

Max Activating Token Index: 800

Text #13

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.2846. Min Act: -0.0001

Data Index: 917184 (C4 (Web Text))

Max Activating Token Index: 132

Text #14

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.2776. Min Act: -0.0001

Data Index: 63108 (C4 (Web Text))

Max Activating Token Index: 539

Text #15

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.2698. Min Act: -0.0001

Data Index: 1342980 (C4 (Web Text))

Max Activating Token Index: 366

Text #16

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.2814. Min Act: -0.0001

Data Index: 1079286 (C4 (Web Text))

Max Activating Token Index: 16

Text #17

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.2807. Min Act: -0.0001

Data Index: 48530 (C4 (Web Text))

Max Activating Token Index: 206

Text #18

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.2707. Min Act: -0.0001

Data Index: 478561 (C4 (Web Text))

Max Activating Token Index: 420

Text #19

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.2736. Min Act: -0.0001

Data Index: 1157640 (C4 (Web Text))

Max Activating Token Index: 691