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

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

Neuron 115 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9134. Min Range: -0.9134

Max Act: 0.9134. Min Act: -0.0001

Data Index: 1057460 (C4 (Web Text))

Max Activating Token Index: 468

Text #1

Max Range: 0.9134. Min Range: -0.9134

Max Act: 0.8207. Min Act: -0.0001

Data Index: 194785 (C4 (Web Text))

Max Activating Token Index: 179

Text #2

Max Range: 0.9134. Min Range: -0.9134

Max Act: 0.7997. Min Act: -0.0001

Data Index: 167873 (C4 (Web Text))

Max Activating Token Index: 78

Text #3

Max Range: 0.9134. Min Range: -0.9134

Max Act: 0.7515. Min Act: -0.0001

Data Index: 358264 (C4 (Web Text))

Max Activating Token Index: 493

Text #4

Max Range: 0.9134. Min Range: -0.9134

Max Act: 0.6940. Min Act: -0.0001

Data Index: 919081 (C4 (Web Text))

Max Activating Token Index: 215

Text #5

Max Range: 0.9134. Min Range: -0.9134

Max Act: 0.6957. Min Act: -0.0001

Data Index: 459088 (C4 (Web Text))

Max Activating Token Index: 421

Text #6

Max Range: 0.9134. Min Range: -0.9134

Max Act: 0.7234. Min Act: -0.0001

Data Index: 1269945 (C4 (Web Text))

Max Activating Token Index: 378

Text #7

Max Range: 0.9134. Min Range: -0.9134

Max Act: 0.6905. Min Act: -0.0001

Data Index: 695036 (C4 (Web Text))

Max Activating Token Index: 388

Text #8

Max Range: 0.9134. Min Range: -0.9134

Max Act: 0.6944. Min Act: -0.0001

Data Index: 784215 (C4 (Web Text))

Max Activating Token Index: 222

Text #9

Max Range: 0.9134. Min Range: -0.9134

Max Act: 0.7307. Min Act: -0.0001

Data Index: 98888 (C4 (Web Text))

Max Activating Token Index: 257

Text #10

Max Range: 0.9134. Min Range: -0.9134

Max Act: 0.6635. Min Act: -0.0001

Data Index: 33974 (C4 (Web Text))

Max Activating Token Index: 290

Text #11

Max Range: 0.9134. Min Range: -0.9134

Max Act: 0.6557. Min Act: -0.0001

Data Index: 1342562 (C4 (Web Text))

Max Activating Token Index: 342

Text #12

Max Range: 0.9134. Min Range: -0.9134

Max Act: 0.6796. Min Act: -0.0001

Data Index: 550433 (C4 (Web Text))

Max Activating Token Index: 918

Text #13

Max Range: 0.9134. Min Range: -0.9134

Max Act: 0.6535. Min Act: -0.0001

Data Index: 324580 (C4 (Web Text))

Max Activating Token Index: 848

Text #14

Max Range: 0.9134. Min Range: -0.9134

Max Act: 0.6338. Min Act: -0.0001

Data Index: 34628 (C4 (Web Text))

Max Activating Token Index: 880

Text #15

Max Range: 0.9134. Min Range: -0.9134

Max Act: 0.6694. Min Act: -0.0001

Data Index: 1087815 (C4 (Web Text))

Max Activating Token Index: 655

Text #16

Max Range: 0.9134. Min Range: -0.9134

Max Act: 0.6535. Min Act: -0.0001

Data Index: 438328 (C4 (Web Text))

Max Activating Token Index: 268

Text #17

Max Range: 0.9134. Min Range: -0.9134

Max Act: 0.6847. Min Act: -0.0001

Data Index: 362651 (C4 (Web Text))

Max Activating Token Index: 401

Text #18

Max Range: 0.9134. Min Range: -0.9134

Max Act: 0.6598. Min Act: -0.0001

Data Index: 508045 (C4 (Web Text))

Max Activating Token Index: 655

Text #19

Max Range: 0.9134. Min Range: -0.9134

Max Act: 0.6557. Min Act: -0.0001

Data Index: 589460 (C4 (Web Text))

Max Activating Token Index: 124