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

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

Neuron 1892 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: 0.4251. Min Range: -0.4251

Max Act: 0.4251. Min Act: -0.0001

Data Index: 1386400 (Python Code)

Max Activating Token Index: 608

Text #1

Max Range: 0.4251. Min Range: -0.4251

Max Act: 0.3938. Min Act: -0.0001

Data Index: 1423103 (Python Code)

Max Activating Token Index: 447

Text #2

Max Range: 0.4251. Min Range: -0.4251

Max Act: 0.3878. Min Act: -0.0001

Data Index: 1656015 (Python Code)

Max Activating Token Index: 454

Text #3

Max Range: 0.4251. Min Range: -0.4251

Max Act: 0.3784. Min Act: -0.0001

Data Index: 1371791 (Python Code)

Max Activating Token Index: 552

Text #4

Max Range: 0.4251. Min Range: -0.4251

Max Act: 0.3489. Min Act: -0.0001

Data Index: 1516228 (Python Code)

Max Activating Token Index: 286

Text #5

Max Range: 0.4251. Min Range: -0.4251

Max Act: 0.3481. Min Act: -0.0001

Data Index: 1517885 (Python Code)

Max Activating Token Index: 449

Text #6

Max Range: 0.4251. Min Range: -0.4251

Max Act: 0.3539. Min Act: -0.0001

Data Index: 1389087 (Python Code)

Max Activating Token Index: 892

Text #7

Max Range: 0.4251. Min Range: -0.4251

Max Act: 0.3410. Min Act: -0.0001

Data Index: 1392004 (Python Code)

Max Activating Token Index: 487

Text #8

Max Range: 0.4251. Min Range: -0.4251

Max Act: 0.3431. Min Act: -0.0001

Data Index: 1588849 (Python Code)

Max Activating Token Index: 590

Text #9

Max Range: 0.4251. Min Range: -0.4251

Max Act: 0.3348. Min Act: -0.0001

Data Index: 1507354 (Python Code)

Max Activating Token Index: 138

Text #10

Max Range: 0.4251. Min Range: -0.4251

Max Act: 0.3238. Min Act: -0.0001

Data Index: 1592275 (Python Code)

Max Activating Token Index: 371

Text #11

Max Range: 0.4251. Min Range: -0.4251

Max Act: 0.3302. Min Act: -0.0001

Data Index: 1626827 (Python Code)

Max Activating Token Index: 1007

Text #12

Max Range: 0.4251. Min Range: -0.4251

Max Act: 0.3240. Min Act: -0.0001

Data Index: 1492907 (Python Code)

Max Activating Token Index: 493

Text #13

Max Range: 0.4251. Min Range: -0.4251

Max Act: 0.3355. Min Act: -0.0001

Data Index: 1504653 (Python Code)

Max Activating Token Index: 192

Text #14

Max Range: 0.4251. Min Range: -0.4251

Max Act: 0.3093. Min Act: -0.0001

Data Index: 1579090 (Python Code)

Max Activating Token Index: 219

Text #15

Max Range: 0.4251. Min Range: -0.4251

Max Act: 0.3103. Min Act: -0.0001

Data Index: 1557782 (Python Code)

Max Activating Token Index: 786

Text #16

Max Range: 0.4251. Min Range: -0.4251

Max Act: 0.3367. Min Act: -0.0001

Data Index: 1614260 (Python Code)

Max Activating Token Index: 57

Text #17

Max Range: 0.4251. Min Range: -0.4251

Max Act: 0.3118. Min Act: -0.0001

Data Index: 1501453 (Python Code)

Max Activating Token Index: 83

Text #18

Max Range: 0.4251. Min Range: -0.4251

Max Act: 0.2995. Min Act: -0.0001

Data Index: 1561328 (Python Code)

Max Activating Token Index: 787

Text #19

Max Range: 0.4251. Min Range: -0.4251

Max Act: 0.3198. Min Act: -0.0001

Data Index: 1438659 (Python Code)

Max Activating Token Index: 888