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

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

Neuron 4134 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.5346. Min Act: -0.0000

Data Index: 496752 (C4 (Web Text))

Max Activating Token Index: 632

Text #1

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.5185. Min Act: -0.0000

Data Index: 168214 (C4 (Web Text))

Max Activating Token Index: 394

Text #2

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.4331. Min Act: -0.0000

Data Index: 1274784 (C4 (Web Text))

Max Activating Token Index: 234

Text #3

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.4511. Min Act: -0.0000

Data Index: 635237 (C4 (Web Text))

Max Activating Token Index: 144

Text #4

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.4342. Min Act: -0.0000

Data Index: 1221514 (C4 (Web Text))

Max Activating Token Index: 217

Text #5

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.4303. Min Act: -0.0000

Data Index: 1306931 (C4 (Web Text))

Max Activating Token Index: 208

Text #6

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.4287. Min Act: -0.0000

Data Index: 191521 (C4 (Web Text))

Max Activating Token Index: 197

Text #7

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.4393. Min Act: -0.0000

Data Index: 946640 (C4 (Web Text))

Max Activating Token Index: 318

Text #8

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.3731. Min Act: -0.0000

Data Index: 1173495 (C4 (Web Text))

Max Activating Token Index: 892

Text #9

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.4171. Min Act: -0.0000

Data Index: 1029251 (C4 (Web Text))

Max Activating Token Index: 228

Text #10

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.4139. Min Act: -0.0000

Data Index: 1026026 (C4 (Web Text))

Max Activating Token Index: 94

Text #11

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.4124. Min Act: -0.0000

Data Index: 222819 (C4 (Web Text))

Max Activating Token Index: 133

Text #12

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.3930. Min Act: -0.0000

Data Index: 885713 (C4 (Web Text))

Max Activating Token Index: 122

Text #13

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.4070. Min Act: -0.0000

Data Index: 614935 (C4 (Web Text))

Max Activating Token Index: 113

Text #14

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.3917. Min Act: -0.0000

Data Index: 253268 (C4 (Web Text))

Max Activating Token Index: 239

Text #15

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.3825. Min Act: -0.0000

Data Index: 1000590 (C4 (Web Text))

Max Activating Token Index: 244

Text #16

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.3815. Min Act: -0.0000

Data Index: 392339 (C4 (Web Text))

Max Activating Token Index: 896

Text #17

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.4074. Min Act: -0.0000

Data Index: 142422 (C4 (Web Text))

Max Activating Token Index: 663

Text #18

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.3685. Min Act: -0.0000

Data Index: 301013 (C4 (Web Text))

Max Activating Token Index: 102

Text #19

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.4072. Min Act: -0.0000

Data Index: 1037438 (C4 (Web Text))

Max Activating Token Index: 388