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

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

Neuron 2960 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7129. Min Range: -1.7129

Max Act: 1.7129. Min Act: -0.0001

Data Index: 1352557 (C4 (Web Text))

Max Activating Token Index: 966

Text #1

Max Range: 1.7129. Min Range: -1.7129

Max Act: 1.5392. Min Act: -0.0001

Data Index: 49243 (C4 (Web Text))

Max Activating Token Index: 1015

Text #2

Max Range: 1.7129. Min Range: -1.7129

Max Act: 1.6215. Min Act: -0.0001

Data Index: 135499 (C4 (Web Text))

Max Activating Token Index: 587

Text #3

Max Range: 1.7129. Min Range: -1.7129

Max Act: 1.5360. Min Act: -0.0001

Data Index: 90940 (C4 (Web Text))

Max Activating Token Index: 732

Text #4

Max Range: 1.7129. Min Range: -1.7129

Max Act: 1.3026. Min Act: -0.0001

Data Index: 19674 (C4 (Web Text))

Max Activating Token Index: 663

Text #5

Max Range: 1.7129. Min Range: -1.7129

Max Act: 1.3703. Min Act: -0.0001

Data Index: 549533 (C4 (Web Text))

Max Activating Token Index: 426

Text #6

Max Range: 1.7129. Min Range: -1.7129

Max Act: 1.4330. Min Act: -0.0001

Data Index: 417727 (C4 (Web Text))

Max Activating Token Index: 870

Text #7

Max Range: 1.7129. Min Range: -1.7129

Max Act: 1.2744. Min Act: -0.0001

Data Index: 342217 (C4 (Web Text))

Max Activating Token Index: 563

Text #8

Max Range: 1.7129. Min Range: -1.7129

Max Act: 1.2357. Min Act: -0.0001

Data Index: 345446 (C4 (Web Text))

Max Activating Token Index: 842

Text #9

Max Range: 1.7129. Min Range: -1.7129

Max Act: 1.2146. Min Act: -0.0001

Data Index: 846738 (C4 (Web Text))

Max Activating Token Index: 898

Text #10

Max Range: 1.7129. Min Range: -1.7129

Max Act: 1.2335. Min Act: -0.0001

Data Index: 840307 (C4 (Web Text))

Max Activating Token Index: 143

Text #11

Max Range: 1.7129. Min Range: -1.7129

Max Act: 1.1962. Min Act: -0.0001

Data Index: 288046 (C4 (Web Text))

Max Activating Token Index: 647

Text #12

Max Range: 1.7129. Min Range: -1.7129

Max Act: 1.2512. Min Act: -0.0001

Data Index: 299123 (C4 (Web Text))

Max Activating Token Index: 435

Text #13

Max Range: 1.7129. Min Range: -1.7129

Max Act: 1.1326. Min Act: -0.0001

Data Index: 595270 (C4 (Web Text))

Max Activating Token Index: 1004

Text #14

Max Range: 1.7129. Min Range: -1.7129

Max Act: 1.1382. Min Act: -0.0001

Data Index: 225025 (C4 (Web Text))

Max Activating Token Index: 157

Text #15

Max Range: 1.7129. Min Range: -1.7129

Max Act: 1.1294. Min Act: -0.0001

Data Index: 784192 (C4 (Web Text))

Max Activating Token Index: 558

Text #16

Max Range: 1.7129. Min Range: -1.7129

Max Act: 1.2112. Min Act: -0.0001

Data Index: 25488 (C4 (Web Text))

Max Activating Token Index: 985

Text #17

Max Range: 1.7129. Min Range: -1.7129

Max Act: 1.0975. Min Act: -0.0001

Data Index: 979390 (C4 (Web Text))

Max Activating Token Index: 274

Text #18

Max Range: 1.7129. Min Range: -1.7129

Max Act: 1.1290. Min Act: -0.0001

Data Index: 554177 (C4 (Web Text))

Max Activating Token Index: 388

Text #19

Max Range: 1.7129. Min Range: -1.7129

Max Act: 1.0305. Min Act: -0.0001

Data Index: 1108413 (C4 (Web Text))

Max Activating Token Index: 995