Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1394 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0859. Min Range: -1.0859

Max Act: 1.0859. Min Act: -0.0001

Data Index: 1289635 (C4 (Web Text))

Max Activating Token Index: 871

Text #1

Max Range: 1.0859. Min Range: -1.0859

Max Act: 0.9500. Min Act: -0.0001

Data Index: 649967 (C4 (Web Text))

Max Activating Token Index: 788

Text #2

Max Range: 1.0859. Min Range: -1.0859

Max Act: 0.8469. Min Act: -0.0001

Data Index: 281377 (C4 (Web Text))

Max Activating Token Index: 728

Text #3

Max Range: 1.0859. Min Range: -1.0859

Max Act: 0.8123. Min Act: -0.0001

Data Index: 499452 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 1.0859. Min Range: -1.0859

Max Act: 0.7860. Min Act: -0.0001

Data Index: 242499 (C4 (Web Text))

Max Activating Token Index: 405

Text #5

Max Range: 1.0859. Min Range: -1.0859

Max Act: 0.7997. Min Act: -0.0001

Data Index: 947521 (C4 (Web Text))

Max Activating Token Index: 435

Text #6

Max Range: 1.0859. Min Range: -1.0859

Max Act: 0.7920. Min Act: -0.0001

Data Index: 1236410 (C4 (Web Text))

Max Activating Token Index: 76

Text #7

Max Range: 1.0859. Min Range: -1.0859

Max Act: 0.7670. Min Act: -0.0001

Data Index: 159642 (C4 (Web Text))

Max Activating Token Index: 917

Text #8

Max Range: 1.0859. Min Range: -1.0859

Max Act: 0.6938. Min Act: -0.0001

Data Index: 650192 (C4 (Web Text))

Max Activating Token Index: 208

Text #9

Max Range: 1.0859. Min Range: -1.0859

Max Act: 0.7376. Min Act: -0.0001

Data Index: 476885 (C4 (Web Text))

Max Activating Token Index: 701

Text #10

Max Range: 1.0859. Min Range: -1.0859

Max Act: 0.7305. Min Act: -0.0001

Data Index: 105725 (C4 (Web Text))

Max Activating Token Index: 128

Text #11

Max Range: 1.0859. Min Range: -1.0859

Max Act: 0.7222. Min Act: -0.0001

Data Index: 1619426 (Python Code)

Max Activating Token Index: 963

Text #12

Max Range: 1.0859. Min Range: -1.0859

Max Act: 0.6903. Min Act: -0.0001

Data Index: 1120458 (C4 (Web Text))

Max Activating Token Index: 880

Text #13

Max Range: 1.0859. Min Range: -1.0859

Max Act: 0.7196. Min Act: -0.0001

Data Index: 1326148 (C4 (Web Text))

Max Activating Token Index: 579

Text #14

Max Range: 1.0859. Min Range: -1.0859

Max Act: 0.7422. Min Act: -0.0001

Data Index: 609323 (C4 (Web Text))

Max Activating Token Index: 680

Text #15

Max Range: 1.0859. Min Range: -1.0859

Max Act: 0.7300. Min Act: -0.0001

Data Index: 1285611 (C4 (Web Text))

Max Activating Token Index: 834

Text #16

Max Range: 1.0859. Min Range: -1.0859

Max Act: 0.7166. Min Act: -0.0001

Data Index: 990179 (C4 (Web Text))

Max Activating Token Index: 712

Text #17

Max Range: 1.0859. Min Range: -1.0859

Max Act: 0.6174. Min Act: -0.0001

Data Index: 648351 (C4 (Web Text))

Max Activating Token Index: 243

Text #18

Max Range: 1.0859. Min Range: -1.0859

Max Act: 0.6464. Min Act: -0.0001

Data Index: 963456 (C4 (Web Text))

Max Activating Token Index: 587

Text #19

Max Range: 1.0859. Min Range: -1.0859

Max Act: 0.6292. Min Act: -0.0001

Data Index: 1168014 (C4 (Web Text))

Max Activating Token Index: 71