Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 993 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3913. Min Range: -0.3913

Max Act: 0.3913. Min Act: -0.0001

Data Index: 344126 (C4 (Web Text))

Max Activating Token Index: 856

Text #1

Max Range: 0.3913. Min Range: -0.3913

Max Act: 0.3677. Min Act: -0.0001

Data Index: 472048 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 0.3913. Min Range: -0.3913

Max Act: 0.3459. Min Act: -0.0001

Data Index: 660654 (C4 (Web Text))

Max Activating Token Index: 61

Text #3

Max Range: 0.3913. Min Range: -0.3913

Max Act: 0.2757. Min Act: -0.0001

Data Index: 507039 (C4 (Web Text))

Max Activating Token Index: 148

Text #4

Max Range: 0.3913. Min Range: -0.3913

Max Act: 0.2624. Min Act: -0.0001

Data Index: 688139 (C4 (Web Text))

Max Activating Token Index: 895

Text #5

Max Range: 0.3913. Min Range: -0.3913

Max Act: 0.2184. Min Act: -0.0001

Data Index: 384660 (C4 (Web Text))

Max Activating Token Index: 613

Text #6

Max Range: 0.3913. Min Range: -0.3913

Max Act: 0.2558. Min Act: -0.0001

Data Index: 501025 (C4 (Web Text))

Max Activating Token Index: 73

Text #7

Max Range: 0.3913. Min Range: -0.3913

Max Act: 0.2677. Min Act: -0.0001

Data Index: 629738 (C4 (Web Text))

Max Activating Token Index: 718

Text #8

Max Range: 0.3913. Min Range: -0.3913

Max Act: 0.2593. Min Act: -0.0001

Data Index: 80931 (C4 (Web Text))

Max Activating Token Index: 57

Text #9

Max Range: 0.3913. Min Range: -0.3913

Max Act: 0.2374. Min Act: -0.0001

Data Index: 231399 (C4 (Web Text))

Max Activating Token Index: 193

Text #10

Max Range: 0.3913. Min Range: -0.3913

Max Act: 0.2654. Min Act: -0.0001

Data Index: 1092069 (C4 (Web Text))

Max Activating Token Index: 523

Text #11

Max Range: 0.3913. Min Range: -0.3913

Max Act: 0.2427. Min Act: -0.0001

Data Index: 168414 (C4 (Web Text))

Max Activating Token Index: 119

Text #12

Max Range: 0.3913. Min Range: -0.3913

Max Act: 0.2324. Min Act: -0.0001

Data Index: 440832 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 0.3913. Min Range: -0.3913

Max Act: 0.2449. Min Act: -0.0001

Data Index: 936401 (C4 (Web Text))

Max Activating Token Index: 112

Text #14

Max Range: 0.3913. Min Range: -0.3913

Max Act: 0.2178. Min Act: -0.0001

Data Index: 526319 (C4 (Web Text))

Max Activating Token Index: 63

Text #15

Max Range: 0.3913. Min Range: -0.3913

Max Act: 0.2518. Min Act: -0.0001

Data Index: 1171133 (C4 (Web Text))

Max Activating Token Index: 229

Text #16

Max Range: 0.3913. Min Range: -0.3913

Max Act: 0.2103. Min Act: -0.0001

Data Index: 897685 (C4 (Web Text))

Max Activating Token Index: 902

Text #17

Max Range: 0.3913. Min Range: -0.3913

Max Act: 0.2431. Min Act: -0.0001

Data Index: 387253 (C4 (Web Text))

Max Activating Token Index: 612

Text #18

Max Range: 0.3913. Min Range: -0.3913

Max Act: 0.2408. Min Act: -0.0001

Data Index: 933188 (C4 (Web Text))

Max Activating Token Index: 570

Text #19

Max Range: 0.3913. Min Range: -0.3913

Max Act: 0.2396. Min Act: -0.0001

Data Index: 1012770 (C4 (Web Text))

Max Activating Token Index: 920