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

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

Neuron 2533 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3887. Min Range: -0.3887

Max Act: 0.3859. Min Act: -0.0001

Data Index: 1287864 (C4 (Web Text))

Max Activating Token Index: 63

Text #1

Max Range: 0.3887. Min Range: -0.3887

Max Act: 0.3887. Min Act: -0.0001

Data Index: 491956 (C4 (Web Text))

Max Activating Token Index: 358

Text #2

Max Range: 0.3887. Min Range: -0.3887

Max Act: 0.3411. Min Act: -0.0001

Data Index: 1102794 (C4 (Web Text))

Max Activating Token Index: 980

Text #3

Max Range: 0.3887. Min Range: -0.3887

Max Act: 0.3360. Min Act: -0.0001

Data Index: 313015 (C4 (Web Text))

Max Activating Token Index: 640

Text #4

Max Range: 0.3887. Min Range: -0.3887

Max Act: 0.3240. Min Act: -0.0001

Data Index: 261913 (C4 (Web Text))

Max Activating Token Index: 308

Text #5

Max Range: 0.3887. Min Range: -0.3887

Max Act: 0.3160. Min Act: -0.0001

Data Index: 1252609 (C4 (Web Text))

Max Activating Token Index: 514

Text #6

Max Range: 0.3887. Min Range: -0.3887

Max Act: 0.3120. Min Act: -0.0001

Data Index: 815215 (C4 (Web Text))

Max Activating Token Index: 71

Text #7

Max Range: 0.3887. Min Range: -0.3887

Max Act: 0.3062. Min Act: -0.0001

Data Index: 1148697 (C4 (Web Text))

Max Activating Token Index: 457

Text #8

Max Range: 0.3887. Min Range: -0.3887

Max Act: 0.2863. Min Act: -0.0001

Data Index: 326376 (C4 (Web Text))

Max Activating Token Index: 715

Text #9

Max Range: 0.3887. Min Range: -0.3887

Max Act: 0.3172. Min Act: -0.0001

Data Index: 111975 (C4 (Web Text))

Max Activating Token Index: 797

Text #10

Max Range: 0.3887. Min Range: -0.3887

Max Act: 0.2947. Min Act: -0.0001

Data Index: 162331 (C4 (Web Text))

Max Activating Token Index: 391

Text #11

Max Range: 0.3887. Min Range: -0.3887

Max Act: 0.2993. Min Act: -0.0001

Data Index: 284182 (C4 (Web Text))

Max Activating Token Index: 502

Text #12

Max Range: 0.3887. Min Range: -0.3887

Max Act: 0.2885. Min Act: -0.0001

Data Index: 549887 (C4 (Web Text))

Max Activating Token Index: 304

Text #13

Max Range: 0.3887. Min Range: -0.3887

Max Act: 0.2889. Min Act: -0.0001

Data Index: 912377 (C4 (Web Text))

Max Activating Token Index: 760

Text #14

Max Range: 0.3887. Min Range: -0.3887

Max Act: 0.2776. Min Act: -0.0001

Data Index: 286682 (C4 (Web Text))

Max Activating Token Index: 895

Text #15

Max Range: 0.3887. Min Range: -0.3887

Max Act: 0.2677. Min Act: -0.0001

Data Index: 849257 (C4 (Web Text))

Max Activating Token Index: 461

Text #16

Max Range: 0.3887. Min Range: -0.3887

Max Act: 0.2733. Min Act: -0.0001

Data Index: 60964 (C4 (Web Text))

Max Activating Token Index: 410

Text #17

Max Range: 0.3887. Min Range: -0.3887

Max Act: 0.2714. Min Act: -0.0001

Data Index: 294173 (C4 (Web Text))

Max Activating Token Index: 310

Text #18

Max Range: 0.3887. Min Range: -0.3887

Max Act: 0.2690. Min Act: -0.0001

Data Index: 754626 (C4 (Web Text))

Max Activating Token Index: 496

Text #19

Max Range: 0.3887. Min Range: -0.3887

Max Act: 0.2674. Min Act: -0.0001

Data Index: 318449 (C4 (Web Text))

Max Activating Token Index: 118