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

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

Neuron 255 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7326. Min Range: -0.7326

Max Act: 0.7326. Min Act: -0.0000

Data Index: 139965 (C4 (Web Text))

Max Activating Token Index: 759

Text #1

Max Range: 0.7326. Min Range: -0.7326

Max Act: 0.7319. Min Act: -0.0000

Data Index: 849961 (C4 (Web Text))

Max Activating Token Index: 126

Text #2

Max Range: 0.7326. Min Range: -0.7326

Max Act: 0.6899. Min Act: -0.0001

Data Index: 886627 (C4 (Web Text))

Max Activating Token Index: 111

Text #3

Max Range: 0.7326. Min Range: -0.7326

Max Act: 0.6722. Min Act: -0.0001

Data Index: 398386 (C4 (Web Text))

Max Activating Token Index: 278

Text #4

Max Range: 0.7326. Min Range: -0.7326

Max Act: 0.6818. Min Act: -0.0001

Data Index: 683758 (C4 (Web Text))

Max Activating Token Index: 292

Text #5

Max Range: 0.7326. Min Range: -0.7326

Max Act: 0.5833. Min Act: -0.0001

Data Index: 340316 (C4 (Web Text))

Max Activating Token Index: 169

Text #6

Max Range: 0.7326. Min Range: -0.7326

Max Act: 0.5867. Min Act: -0.0001

Data Index: 394232 (C4 (Web Text))

Max Activating Token Index: 448

Text #7

Max Range: 0.7326. Min Range: -0.7326

Max Act: 0.6470. Min Act: -0.0001

Data Index: 812379 (C4 (Web Text))

Max Activating Token Index: 660

Text #8

Max Range: 0.7326. Min Range: -0.7326

Max Act: 0.5432. Min Act: -0.0001

Data Index: 620651 (C4 (Web Text))

Max Activating Token Index: 61

Text #9

Max Range: 0.7326. Min Range: -0.7326

Max Act: 0.5772. Min Act: -0.0000

Data Index: 345573 (C4 (Web Text))

Max Activating Token Index: 681

Text #10

Max Range: 0.7326. Min Range: -0.7326

Max Act: 0.5669. Min Act: -0.0001

Data Index: 29850 (C4 (Web Text))

Max Activating Token Index: 879

Text #11

Max Range: 0.7326. Min Range: -0.7326

Max Act: 0.5284. Min Act: -0.0001

Data Index: 1206767 (C4 (Web Text))

Max Activating Token Index: 358

Text #12

Max Range: 0.7326. Min Range: -0.7326

Max Act: 0.5884. Min Act: -0.0001

Data Index: 176946 (C4 (Web Text))

Max Activating Token Index: 759

Text #13

Max Range: 0.7326. Min Range: -0.7326

Max Act: 0.5437. Min Act: -0.0000

Data Index: 449091 (C4 (Web Text))

Max Activating Token Index: 499

Text #14

Max Range: 0.7326. Min Range: -0.7326

Max Act: 0.5401. Min Act: -0.0001

Data Index: 695532 (C4 (Web Text))

Max Activating Token Index: 432

Text #15

Max Range: 0.7326. Min Range: -0.7326

Max Act: 0.5241. Min Act: -0.0000

Data Index: 1154352 (C4 (Web Text))

Max Activating Token Index: 661

Text #16

Max Range: 0.7326. Min Range: -0.7326

Max Act: 0.5213. Min Act: -0.0000

Data Index: 1033042 (C4 (Web Text))

Max Activating Token Index: 974

Text #17

Max Range: 0.7326. Min Range: -0.7326

Max Act: 0.5651. Min Act: -0.0001

Data Index: 611015 (C4 (Web Text))

Max Activating Token Index: 578

Text #18

Max Range: 0.7326. Min Range: -0.7326

Max Act: 0.5379. Min Act: -0.0001

Data Index: 1210898 (C4 (Web Text))

Max Activating Token Index: 634

Text #19

Max Range: 0.7326. Min Range: -0.7326

Max Act: 0.4999. Min Act: -0.0000

Data Index: 755830 (C4 (Web Text))

Max Activating Token Index: 646