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

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

Neuron 2846 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3489. Min Range: -1.3489

Max Act: 1.2574. Min Act: -0.0001

Data Index: 1424068 (Python Code)

Max Activating Token Index: 687

Text #1

Max Range: 1.3489. Min Range: -1.3489

Max Act: 1.3489. Min Act: -0.0001

Data Index: 1025298 (C4 (Web Text))

Max Activating Token Index: 82

Text #2

Max Range: 1.3489. Min Range: -1.3489

Max Act: 1.2628. Min Act: -0.0001

Data Index: 340347 (C4 (Web Text))

Max Activating Token Index: 914

Text #3

Max Range: 1.3489. Min Range: -1.3489

Max Act: 1.2902. Min Act: -0.0001

Data Index: 737816 (C4 (Web Text))

Max Activating Token Index: 335

Text #4

Max Range: 1.3489. Min Range: -1.3489

Max Act: 1.2578. Min Act: -0.0001

Data Index: 574217 (C4 (Web Text))

Max Activating Token Index: 870

Text #5

Max Range: 1.3489. Min Range: -1.3489

Max Act: 1.2986. Min Act: -0.0001

Data Index: 1405391 (Python Code)

Max Activating Token Index: 487

Text #6

Max Range: 1.3489. Min Range: -1.3489

Max Act: 1.2970. Min Act: -0.0001

Data Index: 34346 (C4 (Web Text))

Max Activating Token Index: 487

Text #7

Max Range: 1.3489. Min Range: -1.3489

Max Act: 1.2266. Min Act: -0.0001

Data Index: 451669 (C4 (Web Text))

Max Activating Token Index: 654

Text #8

Max Range: 1.3489. Min Range: -1.3489

Max Act: 1.2981. Min Act: -0.0001

Data Index: 1612325 (Python Code)

Max Activating Token Index: 478

Text #9

Max Range: 1.3489. Min Range: -1.3489

Max Act: 1.2845. Min Act: -0.0001

Data Index: 1090926 (C4 (Web Text))

Max Activating Token Index: 325

Text #10

Max Range: 1.3489. Min Range: -1.3489

Max Act: 1.1989. Min Act: -0.0001

Data Index: 345163 (C4 (Web Text))

Max Activating Token Index: 179

Text #11

Max Range: 1.3489. Min Range: -1.3489

Max Act: 1.2259. Min Act: -0.0001

Data Index: 718063 (C4 (Web Text))

Max Activating Token Index: 297

Text #12

Max Range: 1.3489. Min Range: -1.3489

Max Act: 1.2961. Min Act: -0.0001

Data Index: 734415 (C4 (Web Text))

Max Activating Token Index: 541

Text #13

Max Range: 1.3489. Min Range: -1.3489

Max Act: 1.1057. Min Act: -0.0001

Data Index: 1092556 (C4 (Web Text))

Max Activating Token Index: 259

Text #14

Max Range: 1.3489. Min Range: -1.3489

Max Act: 1.2301. Min Act: -0.0001

Data Index: 1522329 (Python Code)

Max Activating Token Index: 522

Text #15

Max Range: 1.3489. Min Range: -1.3489

Max Act: 1.2713. Min Act: -0.0001

Data Index: 1095845 (C4 (Web Text))

Max Activating Token Index: 508

Text #16

Max Range: 1.3489. Min Range: -1.3489

Max Act: 1.2677. Min Act: -0.0001

Data Index: 610606 (C4 (Web Text))

Max Activating Token Index: 860

Text #17

Max Range: 1.3489. Min Range: -1.3489

Max Act: 1.2660. Min Act: -0.0001

Data Index: 710023 (C4 (Web Text))

Max Activating Token Index: 143

Text #18

Max Range: 1.3489. Min Range: -1.3489

Max Act: 1.2203. Min Act: -0.0001

Data Index: 1214453 (C4 (Web Text))

Max Activating Token Index: 296

Text #19

Max Range: 1.3489. Min Range: -1.3489

Max Act: 1.2816. Min Act: -0.0001

Data Index: 27732 (C4 (Web Text))

Max Activating Token Index: 345