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

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

Neuron 773 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: 1.2752. Min Range: -1.2752

Max Act: 1.2752. Min Act: -0.0001

Data Index: 1211276 (C4 (Web Text))

Max Activating Token Index: 620

Text #1

Max Range: 1.2752. Min Range: -1.2752

Max Act: 1.2384. Min Act: -0.0001

Data Index: 511081 (C4 (Web Text))

Max Activating Token Index: 544

Text #2

Max Range: 1.2752. Min Range: -1.2752

Max Act: 1.0864. Min Act: -0.0001

Data Index: 1351788 (C4 (Web Text))

Max Activating Token Index: 163

Text #3

Max Range: 1.2752. Min Range: -1.2752

Max Act: 1.0716. Min Act: -0.0001

Data Index: 836399 (C4 (Web Text))

Max Activating Token Index: 354

Text #4

Max Range: 1.2752. Min Range: -1.2752

Max Act: 1.1331. Min Act: -0.0001

Data Index: 571314 (C4 (Web Text))

Max Activating Token Index: 283

Text #5

Max Range: 1.2752. Min Range: -1.2752

Max Act: 1.0588. Min Act: -0.0001

Data Index: 736986 (C4 (Web Text))

Max Activating Token Index: 1004

Text #6

Max Range: 1.2752. Min Range: -1.2752

Max Act: 1.0050. Min Act: -0.0001

Data Index: 826421 (C4 (Web Text))

Max Activating Token Index: 419

Text #7

Max Range: 1.2752. Min Range: -1.2752

Max Act: 1.0275. Min Act: -0.0001

Data Index: 1180272 (C4 (Web Text))

Max Activating Token Index: 278

Text #8

Max Range: 1.2752. Min Range: -1.2752

Max Act: 0.9891. Min Act: -0.0001

Data Index: 959929 (C4 (Web Text))

Max Activating Token Index: 302

Text #9

Max Range: 1.2752. Min Range: -1.2752

Max Act: 0.9312. Min Act: -0.0001

Data Index: 1285471 (C4 (Web Text))

Max Activating Token Index: 534

Text #10

Max Range: 1.2752. Min Range: -1.2752

Max Act: 0.9661. Min Act: -0.0001

Data Index: 1006491 (C4 (Web Text))

Max Activating Token Index: 807

Text #11

Max Range: 1.2752. Min Range: -1.2752

Max Act: 0.9575. Min Act: -0.0001

Data Index: 1194108 (C4 (Web Text))

Max Activating Token Index: 256

Text #12

Max Range: 1.2752. Min Range: -1.2752

Max Act: 1.0476. Min Act: -0.0001

Data Index: 1300152 (C4 (Web Text))

Max Activating Token Index: 963

Text #13

Max Range: 1.2752. Min Range: -1.2752

Max Act: 0.9696. Min Act: -0.0001

Data Index: 1094936 (C4 (Web Text))

Max Activating Token Index: 139

Text #14

Max Range: 1.2752. Min Range: -1.2752

Max Act: 0.9347. Min Act: -0.0001

Data Index: 414268 (C4 (Web Text))

Max Activating Token Index: 171

Text #15

Max Range: 1.2752. Min Range: -1.2752

Max Act: 0.9940. Min Act: -0.0001

Data Index: 131530 (C4 (Web Text))

Max Activating Token Index: 259

Text #16

Max Range: 1.2752. Min Range: -1.2752

Max Act: 0.9966. Min Act: -0.0001

Data Index: 1296906 (C4 (Web Text))

Max Activating Token Index: 7

Text #17

Max Range: 1.2752. Min Range: -1.2752

Max Act: 1.0279. Min Act: -0.0001

Data Index: 921006 (C4 (Web Text))

Max Activating Token Index: 755

Text #18

Max Range: 1.2752. Min Range: -1.2752

Max Act: 0.9946. Min Act: -0.0001

Data Index: 377540 (C4 (Web Text))

Max Activating Token Index: 835

Text #19

Max Range: 1.2752. Min Range: -1.2752

Max Act: 0.8970. Min Act: -0.0001

Data Index: 1346785 (C4 (Web Text))

Max Activating Token Index: 908