Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2370 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.1286. Min Range: -1.1286

Max Act: 1.1286. Min Act: -0.0001

Data Index: 44289 (C4 (Web Text))

Max Activating Token Index: 451

Text #1

Max Range: 1.1286. Min Range: -1.1286

Max Act: 1.0153. Min Act: -0.0001

Data Index: 853774 (C4 (Web Text))

Max Activating Token Index: 456

Text #2

Max Range: 1.1286. Min Range: -1.1286

Max Act: 1.0036. Min Act: -0.0001

Data Index: 30981 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 1.1286. Min Range: -1.1286

Max Act: 0.9436. Min Act: -0.0001

Data Index: 248171 (C4 (Web Text))

Max Activating Token Index: 79

Text #4

Max Range: 1.1286. Min Range: -1.1286

Max Act: 0.8615. Min Act: -0.0001

Data Index: 158712 (C4 (Web Text))

Max Activating Token Index: 741

Text #5

Max Range: 1.1286. Min Range: -1.1286

Max Act: 0.8392. Min Act: -0.0001

Data Index: 1122784 (C4 (Web Text))

Max Activating Token Index: 668

Text #6

Max Range: 1.1286. Min Range: -1.1286

Max Act: 0.9180. Min Act: -0.0001

Data Index: 1020733 (C4 (Web Text))

Max Activating Token Index: 143

Text #7

Max Range: 1.1286. Min Range: -1.1286

Max Act: 0.8370. Min Act: -0.0001

Data Index: 10470 (C4 (Web Text))

Max Activating Token Index: 154

Text #8

Max Range: 1.1286. Min Range: -1.1286

Max Act: 0.8432. Min Act: -0.0001

Data Index: 208789 (C4 (Web Text))

Max Activating Token Index: 373

Text #9

Max Range: 1.1286. Min Range: -1.1286

Max Act: 0.8626. Min Act: -0.0001

Data Index: 350966 (C4 (Web Text))

Max Activating Token Index: 481

Text #10

Max Range: 1.1286. Min Range: -1.1286

Max Act: 0.7955. Min Act: -0.0001

Data Index: 560836 (C4 (Web Text))

Max Activating Token Index: 325

Text #11

Max Range: 1.1286. Min Range: -1.1286

Max Act: 0.8601. Min Act: -0.0001

Data Index: 189244 (C4 (Web Text))

Max Activating Token Index: 944

Text #12

Max Range: 1.1286. Min Range: -1.1286

Max Act: 0.7732. Min Act: -0.0001

Data Index: 747960 (C4 (Web Text))

Max Activating Token Index: 764

Text #13

Max Range: 1.1286. Min Range: -1.1286

Max Act: 0.8860. Min Act: -0.0001

Data Index: 1222328 (C4 (Web Text))

Max Activating Token Index: 208

Text #14

Max Range: 1.1286. Min Range: -1.1286

Max Act: 0.8844. Min Act: -0.0001

Data Index: 19168 (C4 (Web Text))

Max Activating Token Index: 956

Text #15

Max Range: 1.1286. Min Range: -1.1286

Max Act: 0.7702. Min Act: -0.0001

Data Index: 42406 (C4 (Web Text))

Max Activating Token Index: 277

Text #16

Max Range: 1.1286. Min Range: -1.1286

Max Act: 0.8135. Min Act: -0.0001

Data Index: 806510 (C4 (Web Text))

Max Activating Token Index: 798

Text #17

Max Range: 1.1286. Min Range: -1.1286

Max Act: 0.8084. Min Act: -0.0001

Data Index: 531426 (C4 (Web Text))

Max Activating Token Index: 40

Text #18

Max Range: 1.1286. Min Range: -1.1286

Max Act: 0.8061. Min Act: -0.0001

Data Index: 189720 (C4 (Web Text))

Max Activating Token Index: 626

Text #19

Max Range: 1.1286. Min Range: -1.1286

Max Act: 0.7984. Min Act: -0.0001

Data Index: 963773 (C4 (Web Text))

Max Activating Token Index: 48