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

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

Neuron 1196 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2259. Min Range: -1.2259

Max Act: 1.2259. Min Act: -0.0001

Data Index: 893305 (C4 (Web Text))

Max Activating Token Index: 826

Text #1

Max Range: 1.2259. Min Range: -1.2259

Max Act: 1.1488. Min Act: -0.0001

Data Index: 468877 (C4 (Web Text))

Max Activating Token Index: 589

Text #2

Max Range: 1.2259. Min Range: -1.2259

Max Act: 1.1116. Min Act: -0.0001

Data Index: 487556 (C4 (Web Text))

Max Activating Token Index: 192

Text #3

Max Range: 1.2259. Min Range: -1.2259

Max Act: 1.0779. Min Act: -0.0001

Data Index: 1211851 (C4 (Web Text))

Max Activating Token Index: 871

Text #4

Max Range: 1.2259. Min Range: -1.2259

Max Act: 1.1026. Min Act: -0.0001

Data Index: 48056 (C4 (Web Text))

Max Activating Token Index: 474

Text #5

Max Range: 1.2259. Min Range: -1.2259

Max Act: 1.0715. Min Act: -0.0001

Data Index: 849593 (C4 (Web Text))

Max Activating Token Index: 392

Text #6

Max Range: 1.2259. Min Range: -1.2259

Max Act: 1.0901. Min Act: -0.0001

Data Index: 1090145 (C4 (Web Text))

Max Activating Token Index: 993

Text #7

Max Range: 1.2259. Min Range: -1.2259

Max Act: 1.0152. Min Act: -0.0001

Data Index: 1316019 (C4 (Web Text))

Max Activating Token Index: 521

Text #8

Max Range: 1.2259. Min Range: -1.2259

Max Act: 1.0478. Min Act: -0.0001

Data Index: 293639 (C4 (Web Text))

Max Activating Token Index: 293

Text #9

Max Range: 1.2259. Min Range: -1.2259

Max Act: 1.0450. Min Act: -0.0001

Data Index: 583830 (C4 (Web Text))

Max Activating Token Index: 903

Text #10

Max Range: 1.2259. Min Range: -1.2259

Max Act: 1.0326. Min Act: -0.0001

Data Index: 451042 (C4 (Web Text))

Max Activating Token Index: 622

Text #11

Max Range: 1.2259. Min Range: -1.2259

Max Act: 1.0728. Min Act: -0.0001

Data Index: 305082 (C4 (Web Text))

Max Activating Token Index: 763

Text #12

Max Range: 1.2259. Min Range: -1.2259

Max Act: 1.0133. Min Act: -0.0001

Data Index: 1242288 (C4 (Web Text))

Max Activating Token Index: 442

Text #13

Max Range: 1.2259. Min Range: -1.2259

Max Act: 0.9817. Min Act: -0.0001

Data Index: 36343 (C4 (Web Text))

Max Activating Token Index: 577

Text #14

Max Range: 1.2259. Min Range: -1.2259

Max Act: 1.0175. Min Act: -0.0001

Data Index: 54094 (C4 (Web Text))

Max Activating Token Index: 361

Text #15

Max Range: 1.2259. Min Range: -1.2259

Max Act: 0.9819. Min Act: -0.0001

Data Index: 803644 (C4 (Web Text))

Max Activating Token Index: 418

Text #16

Max Range: 1.2259. Min Range: -1.2259

Max Act: 1.0438. Min Act: -0.0001

Data Index: 756460 (C4 (Web Text))

Max Activating Token Index: 985

Text #17

Max Range: 1.2259. Min Range: -1.2259

Max Act: 0.9475. Min Act: -0.0001

Data Index: 45416 (C4 (Web Text))

Max Activating Token Index: 753

Text #18

Max Range: 1.2259. Min Range: -1.2259

Max Act: 0.9557. Min Act: -0.0001

Data Index: 392397 (C4 (Web Text))

Max Activating Token Index: 266

Text #19

Max Range: 1.2259. Min Range: -1.2259

Max Act: 1.0025. Min Act: -0.0001

Data Index: 1333958 (C4 (Web Text))

Max Activating Token Index: 308