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

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

Neuron 1156 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: 5.5422. Min Range: -5.5422

Max Act: 5.5422. Min Act: -0.0001

Data Index: 317613 (C4 (Web Text))

Max Activating Token Index: 754

Text #1

Max Range: 5.5422. Min Range: -5.5422

Max Act: 5.0871. Min Act: -0.0001

Data Index: 625690 (C4 (Web Text))

Max Activating Token Index: 236

Text #2

Max Range: 5.5422. Min Range: -5.5422

Max Act: 4.6538. Min Act: -0.0001

Data Index: 484725 (C4 (Web Text))

Max Activating Token Index: 453

Text #3

Max Range: 5.5422. Min Range: -5.5422

Max Act: 4.8211. Min Act: -0.0001

Data Index: 877683 (C4 (Web Text))

Max Activating Token Index: 413

Text #4

Max Range: 5.5422. Min Range: -5.5422

Max Act: 4.2507. Min Act: -0.0001

Data Index: 1287422 (C4 (Web Text))

Max Activating Token Index: 69

Text #5

Max Range: 5.5422. Min Range: -5.5422

Max Act: 4.2280. Min Act: -0.0001

Data Index: 899213 (C4 (Web Text))

Max Activating Token Index: 553

Text #6

Max Range: 5.5422. Min Range: -5.5422

Max Act: 4.3026. Min Act: -0.0001

Data Index: 576292 (C4 (Web Text))

Max Activating Token Index: 470

Text #7

Max Range: 5.5422. Min Range: -5.5422

Max Act: 4.1270. Min Act: -0.0001

Data Index: 213526 (C4 (Web Text))

Max Activating Token Index: 451

Text #8

Max Range: 5.5422. Min Range: -5.5422

Max Act: 4.0585. Min Act: -0.0001

Data Index: 253867 (C4 (Web Text))

Max Activating Token Index: 354

Text #9

Max Range: 5.5422. Min Range: -5.5422

Max Act: 4.3045. Min Act: -0.0001

Data Index: 544765 (C4 (Web Text))

Max Activating Token Index: 940

Text #10

Max Range: 5.5422. Min Range: -5.5422

Max Act: 3.9171. Min Act: -0.0001

Data Index: 1105404 (C4 (Web Text))

Max Activating Token Index: 129

Text #11

Max Range: 5.5422. Min Range: -5.5422

Max Act: 4.4233. Min Act: -0.0001

Data Index: 308350 (C4 (Web Text))

Max Activating Token Index: 727

Text #12

Max Range: 5.5422. Min Range: -5.5422

Max Act: 3.7996. Min Act: -0.0001

Data Index: 1187840 (C4 (Web Text))

Max Activating Token Index: 642

Text #13

Max Range: 5.5422. Min Range: -5.5422

Max Act: 4.0752. Min Act: -0.0001

Data Index: 1213645 (C4 (Web Text))

Max Activating Token Index: 442

Text #14

Max Range: 5.5422. Min Range: -5.5422

Max Act: 3.9039. Min Act: -0.0001

Data Index: 40122 (C4 (Web Text))

Max Activating Token Index: 479

Text #15

Max Range: 5.5422. Min Range: -5.5422

Max Act: 3.7562. Min Act: -0.0001

Data Index: 286259 (C4 (Web Text))

Max Activating Token Index: 124

Text #16

Max Range: 5.5422. Min Range: -5.5422

Max Act: 3.9073. Min Act: -0.0001

Data Index: 1049754 (C4 (Web Text))

Max Activating Token Index: 528

Text #17

Max Range: 5.5422. Min Range: -5.5422

Max Act: 3.8797. Min Act: -0.0001

Data Index: 219767 (C4 (Web Text))

Max Activating Token Index: 421

Text #18

Max Range: 5.5422. Min Range: -5.5422

Max Act: 3.7266. Min Act: -0.0001

Data Index: 487474 (C4 (Web Text))

Max Activating Token Index: 478

Text #19

Max Range: 5.5422. Min Range: -5.5422

Max Act: 4.0318. Min Act: -0.0001

Data Index: 768820 (C4 (Web Text))

Max Activating Token Index: 394