Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 382 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.3233. Min Range: -0.3233

Max Act: 0.3233. Min Act: -0.0003

Data Index: 1582865 (Python Code)

Max Activating Token Index: 520

Text #1

Max Range: 0.3233. Min Range: -0.3233

Max Act: 0.3223. Min Act: -0.0004

Data Index: 1568525 (Python Code)

Max Activating Token Index: 790

Text #2

Max Range: 0.3233. Min Range: -0.3233

Max Act: 0.3198. Min Act: -0.0003

Data Index: 1482179 (Python Code)

Max Activating Token Index: 459

Text #3

Max Range: 0.3233. Min Range: -0.3233

Max Act: 0.3120. Min Act: -0.0003

Data Index: 1424812 (Python Code)

Max Activating Token Index: 189

Text #4

Max Range: 0.3233. Min Range: -0.3233

Max Act: 0.3217. Min Act: -0.0003

Data Index: 1626775 (Python Code)

Max Activating Token Index: 838

Text #5

Max Range: 0.3233. Min Range: -0.3233

Max Act: 0.3085. Min Act: -0.0003

Data Index: 1459304 (Python Code)

Max Activating Token Index: 405

Text #6

Max Range: 0.3233. Min Range: -0.3233

Max Act: 0.2983. Min Act: -0.0003

Data Index: 1454451 (Python Code)

Max Activating Token Index: 734

Text #7

Max Range: 0.3233. Min Range: -0.3233

Max Act: 0.3081. Min Act: -0.0003

Data Index: 1375817 (Python Code)

Max Activating Token Index: 496

Text #8

Max Range: 0.3233. Min Range: -0.3233

Max Act: 0.3070. Min Act: -0.0003

Data Index: 1622003 (Python Code)

Max Activating Token Index: 638

Text #9

Max Range: 0.3233. Min Range: -0.3233

Max Act: 0.2963. Min Act: -0.0003

Data Index: 1378060 (Python Code)

Max Activating Token Index: 182

Text #10

Max Range: 0.3233. Min Range: -0.3233

Max Act: 0.3021. Min Act: -0.0003

Data Index: 1436313 (Python Code)

Max Activating Token Index: 482

Text #11

Max Range: 0.3233. Min Range: -0.3233

Max Act: 0.2882. Min Act: -0.0003

Data Index: 1416478 (Python Code)

Max Activating Token Index: 545

Text #12

Max Range: 0.3233. Min Range: -0.3233

Max Act: 0.2981. Min Act: -0.0003

Data Index: 1652415 (Python Code)

Max Activating Token Index: 838

Text #13

Max Range: 0.3233. Min Range: -0.3233

Max Act: 0.2983. Min Act: -0.0003

Data Index: 1558454 (Python Code)

Max Activating Token Index: 889

Text #14

Max Range: 0.3233. Min Range: -0.3233

Max Act: 0.2964. Min Act: -0.0003

Data Index: 1425039 (Python Code)

Max Activating Token Index: 801

Text #15

Max Range: 0.3233. Min Range: -0.3233

Max Act: 0.2954. Min Act: -0.0003

Data Index: 1372016 (Python Code)

Max Activating Token Index: 576

Text #16

Max Range: 0.3233. Min Range: -0.3233

Max Act: 0.2938. Min Act: -0.0003

Data Index: 1598360 (Python Code)

Max Activating Token Index: 179

Text #17

Max Range: 0.3233. Min Range: -0.3233

Max Act: 0.2817. Min Act: -0.0003

Data Index: 1425757 (Python Code)

Max Activating Token Index: 845

Text #18

Max Range: 0.3233. Min Range: -0.3233

Max Act: 0.2895. Min Act: -0.0003

Data Index: 1496935 (Python Code)

Max Activating Token Index: 579

Text #19

Max Range: 0.3233. Min Range: -0.3233

Max Act: 0.2890. Min Act: -0.0003

Data Index: 1548284 (Python Code)

Max Activating Token Index: 169