Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3175 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5292. Min Range: -0.5292

Max Act: 0.5292. Min Act: -0.0000

Data Index: 531667 (C4 (Web Text))

Max Activating Token Index: 519

Text #1

Max Range: 0.5292. Min Range: -0.5292

Max Act: 0.5081. Min Act: -0.0000

Data Index: 1274027 (C4 (Web Text))

Max Activating Token Index: 509

Text #2

Max Range: 0.5292. Min Range: -0.5292

Max Act: 0.4917. Min Act: -0.0000

Data Index: 182885 (C4 (Web Text))

Max Activating Token Index: 127

Text #3

Max Range: 0.5292. Min Range: -0.5292

Max Act: 0.4834. Min Act: 0.0000

Data Index: 337308 (C4 (Web Text))

Max Activating Token Index: 92

Text #4

Max Range: 0.5292. Min Range: -0.5292

Max Act: 0.4743. Min Act: -0.0001

Data Index: 871804 (C4 (Web Text))

Max Activating Token Index: 182

Text #5

Max Range: 0.5292. Min Range: -0.5292

Max Act: 0.4499. Min Act: -0.0000

Data Index: 888651 (C4 (Web Text))

Max Activating Token Index: 955

Text #6

Max Range: 0.5292. Min Range: -0.5292

Max Act: 0.4410. Min Act: -0.0000

Data Index: 280915 (C4 (Web Text))

Max Activating Token Index: 171

Text #7

Max Range: 0.5292. Min Range: -0.5292

Max Act: 0.4506. Min Act: -0.0001

Data Index: 166923 (C4 (Web Text))

Max Activating Token Index: 72

Text #8

Max Range: 0.5292. Min Range: -0.5292

Max Act: 0.4489. Min Act: -0.0000

Data Index: 1122236 (C4 (Web Text))

Max Activating Token Index: 590

Text #9

Max Range: 0.5292. Min Range: -0.5292

Max Act: 0.4213. Min Act: -0.0000

Data Index: 420448 (C4 (Web Text))

Max Activating Token Index: 896

Text #10

Max Range: 0.5292. Min Range: -0.5292

Max Act: 0.4428. Min Act: -0.0000

Data Index: 100081 (C4 (Web Text))

Max Activating Token Index: 927

Text #11

Max Range: 0.5292. Min Range: -0.5292

Max Act: 0.4282. Min Act: -0.0001

Data Index: 518485 (C4 (Web Text))

Max Activating Token Index: 71

Text #12

Max Range: 0.5292. Min Range: -0.5292

Max Act: 0.4122. Min Act: -0.0000

Data Index: 126512 (C4 (Web Text))

Max Activating Token Index: 695

Text #13

Max Range: 0.5292. Min Range: -0.5292

Max Act: 0.4204. Min Act: 0.0000

Data Index: 891356 (C4 (Web Text))

Max Activating Token Index: 475

Text #14

Max Range: 0.5292. Min Range: -0.5292

Max Act: 0.4150. Min Act: -0.0000

Data Index: 1108928 (C4 (Web Text))

Max Activating Token Index: 531

Text #15

Max Range: 0.5292. Min Range: -0.5292

Max Act: 0.4122. Min Act: -0.0000

Data Index: 1105692 (C4 (Web Text))

Max Activating Token Index: 77

Text #16

Max Range: 0.5292. Min Range: -0.5292

Max Act: 0.4072. Min Act: -0.0001

Data Index: 883440 (C4 (Web Text))

Max Activating Token Index: 670

Text #17

Max Range: 0.5292. Min Range: -0.5292

Max Act: 0.4163. Min Act: -0.0000

Data Index: 1162131 (C4 (Web Text))

Max Activating Token Index: 752

Text #18

Max Range: 0.5292. Min Range: -0.5292

Max Act: 0.3891. Min Act: -0.0001

Data Index: 1309088 (C4 (Web Text))

Max Activating Token Index: 37

Text #19

Max Range: 0.5292. Min Range: -0.5292

Max Act: 0.3977. Min Act: -0.0000

Data Index: 1082599 (C4 (Web Text))

Max Activating Token Index: 193