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

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

Neuron 851 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8236. Min Range: -1.8236

Max Act: 1.8236. Min Act: -0.0001

Data Index: 1197780 (C4 (Web Text))

Max Activating Token Index: 507

Text #1

Max Range: 1.8236. Min Range: -1.8236

Max Act: 1.6881. Min Act: -0.0001

Data Index: 512494 (C4 (Web Text))

Max Activating Token Index: 836

Text #2

Max Range: 1.8236. Min Range: -1.8236

Max Act: 1.5292. Min Act: -0.0001

Data Index: 1153364 (C4 (Web Text))

Max Activating Token Index: 429

Text #3

Max Range: 1.8236. Min Range: -1.8236

Max Act: 1.3078. Min Act: -0.0001

Data Index: 1027363 (C4 (Web Text))

Max Activating Token Index: 525

Text #4

Max Range: 1.8236. Min Range: -1.8236

Max Act: 1.2787. Min Act: -0.0001

Data Index: 1282585 (C4 (Web Text))

Max Activating Token Index: 315

Text #5

Max Range: 1.8236. Min Range: -1.8236

Max Act: 1.4250. Min Act: -0.0001

Data Index: 40267 (C4 (Web Text))

Max Activating Token Index: 554

Text #6

Max Range: 1.8236. Min Range: -1.8236

Max Act: 1.3091. Min Act: -0.0001

Data Index: 373567 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 1.8236. Min Range: -1.8236

Max Act: 1.2688. Min Act: -0.0001

Data Index: 216995 (C4 (Web Text))

Max Activating Token Index: 916

Text #8

Max Range: 1.8236. Min Range: -1.8236

Max Act: 1.2896. Min Act: -0.0001

Data Index: 523144 (C4 (Web Text))

Max Activating Token Index: 150

Text #9

Max Range: 1.8236. Min Range: -1.8236

Max Act: 1.2232. Min Act: -0.0001

Data Index: 658415 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 1.8236. Min Range: -1.8236

Max Act: 1.1115. Min Act: -0.0000

Data Index: 1266318 (C4 (Web Text))

Max Activating Token Index: 619

Text #11

Max Range: 1.8236. Min Range: -1.8236

Max Act: 1.1026. Min Act: -0.0001

Data Index: 587767 (C4 (Web Text))

Max Activating Token Index: 429

Text #12

Max Range: 1.8236. Min Range: -1.8236

Max Act: 1.1269. Min Act: -0.0001

Data Index: 868313 (C4 (Web Text))

Max Activating Token Index: 945

Text #13

Max Range: 1.8236. Min Range: -1.8236

Max Act: 1.1114. Min Act: -0.0001

Data Index: 1036717 (C4 (Web Text))

Max Activating Token Index: 450

Text #14

Max Range: 1.8236. Min Range: -1.8236

Max Act: 1.0744. Min Act: -0.0001

Data Index: 1010977 (C4 (Web Text))

Max Activating Token Index: 168

Text #15

Max Range: 1.8236. Min Range: -1.8236

Max Act: 1.0656. Min Act: -0.0001

Data Index: 607075 (C4 (Web Text))

Max Activating Token Index: 765

Text #16

Max Range: 1.8236. Min Range: -1.8236

Max Act: 1.0614. Min Act: -0.0001

Data Index: 351748 (C4 (Web Text))

Max Activating Token Index: 69

Text #17

Max Range: 1.8236. Min Range: -1.8236

Max Act: 1.0071. Min Act: -0.0001

Data Index: 1058443 (C4 (Web Text))

Max Activating Token Index: 317

Text #18

Max Range: 1.8236. Min Range: -1.8236

Max Act: 1.0518. Min Act: -0.0001

Data Index: 293881 (C4 (Web Text))

Max Activating Token Index: 581

Text #19

Max Range: 1.8236. Min Range: -1.8236

Max Act: 1.0819. Min Act: -0.0001

Data Index: 494690 (C4 (Web Text))

Max Activating Token Index: 116