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

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

Neuron 2580 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: 3.8470. Min Range: -3.8470

Max Act: 3.8470. Min Act: -0.0001

Data Index: 149700 (C4 (Web Text))

Max Activating Token Index: 538

Text #1

Max Range: 3.8470. Min Range: -3.8470

Max Act: 3.5879. Min Act: -0.0001

Data Index: 1115424 (C4 (Web Text))

Max Activating Token Index: 1013

Text #2

Max Range: 3.8470. Min Range: -3.8470

Max Act: 3.2685. Min Act: -0.0001

Data Index: 32121 (C4 (Web Text))

Max Activating Token Index: 381

Text #3

Max Range: 3.8470. Min Range: -3.8470

Max Act: 3.2687. Min Act: -0.0001

Data Index: 493597 (C4 (Web Text))

Max Activating Token Index: 114

Text #4

Max Range: 3.8470. Min Range: -3.8470

Max Act: 3.3397. Min Act: -0.0001

Data Index: 220916 (C4 (Web Text))

Max Activating Token Index: 415

Text #5

Max Range: 3.8470. Min Range: -3.8470

Max Act: 3.2808. Min Act: -0.0001

Data Index: 137802 (C4 (Web Text))

Max Activating Token Index: 353

Text #6

Max Range: 3.8470. Min Range: -3.8470

Max Act: 2.9509. Min Act: -0.0001

Data Index: 709898 (C4 (Web Text))

Max Activating Token Index: 408

Text #7

Max Range: 3.8470. Min Range: -3.8470

Max Act: 2.9484. Min Act: -0.0001

Data Index: 39626 (C4 (Web Text))

Max Activating Token Index: 603

Text #8

Max Range: 3.8470. Min Range: -3.8470

Max Act: 3.0753. Min Act: -0.0001

Data Index: 863392 (C4 (Web Text))

Max Activating Token Index: 650

Text #9

Max Range: 3.8470. Min Range: -3.8470

Max Act: 2.9415. Min Act: -0.0001

Data Index: 287859 (C4 (Web Text))

Max Activating Token Index: 652

Text #10

Max Range: 3.8470. Min Range: -3.8470

Max Act: 3.0003. Min Act: -0.0001

Data Index: 189641 (C4 (Web Text))

Max Activating Token Index: 231

Text #11

Max Range: 3.8470. Min Range: -3.8470

Max Act: 2.8081. Min Act: -0.0001

Data Index: 1059481 (C4 (Web Text))

Max Activating Token Index: 321

Text #12

Max Range: 3.8470. Min Range: -3.8470

Max Act: 2.8315. Min Act: -0.0001

Data Index: 958631 (C4 (Web Text))

Max Activating Token Index: 887

Text #13

Max Range: 3.8470. Min Range: -3.8470

Max Act: 2.8063. Min Act: -0.0001

Data Index: 294168 (C4 (Web Text))

Max Activating Token Index: 224

Text #14

Max Range: 3.8470. Min Range: -3.8470

Max Act: 2.9028. Min Act: -0.0001

Data Index: 96534 (C4 (Web Text))

Max Activating Token Index: 908

Text #15

Max Range: 3.8470. Min Range: -3.8470

Max Act: 2.8204. Min Act: -0.0001

Data Index: 589240 (C4 (Web Text))

Max Activating Token Index: 475

Text #16

Max Range: 3.8470. Min Range: -3.8470

Max Act: 2.9821. Min Act: -0.0001

Data Index: 761043 (C4 (Web Text))

Max Activating Token Index: 142

Text #17

Max Range: 3.8470. Min Range: -3.8470

Max Act: 2.8362. Min Act: -0.0001

Data Index: 302594 (C4 (Web Text))

Max Activating Token Index: 465

Text #18

Max Range: 3.8470. Min Range: -3.8470

Max Act: 2.7997. Min Act: -0.0001

Data Index: 369020 (C4 (Web Text))

Max Activating Token Index: 664

Text #19

Max Range: 3.8470. Min Range: -3.8470

Max Act: 2.9375. Min Act: -0.0001

Data Index: 1103438 (C4 (Web Text))

Max Activating Token Index: 382