Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3588 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.6075. Min Act: -0.0002

Data Index: 1652478 (Python Code)

Max Activating Token Index: 151

Text #1

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.5197. Min Act: -0.0002

Data Index: 495767 (C4 (Web Text))

Max Activating Token Index: 473

Text #2

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.5063. Min Act: -0.0002

Data Index: 1445525 (Python Code)

Max Activating Token Index: 619

Text #3

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.4659. Min Act: -0.0002

Data Index: 947389 (C4 (Web Text))

Max Activating Token Index: 548

Text #4

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.5153. Min Act: -0.0002

Data Index: 1489937 (Python Code)

Max Activating Token Index: 500

Text #5

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.4358. Min Act: -0.0002

Data Index: 215167 (C4 (Web Text))

Max Activating Token Index: 299

Text #6

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.4185. Min Act: -0.0002

Data Index: 1073784 (C4 (Web Text))

Max Activating Token Index: 504

Text #7

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.3893. Min Act: -0.0002

Data Index: 1461623 (Python Code)

Max Activating Token Index: 62

Text #8

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.3804. Min Act: -0.0002

Data Index: 1141626 (C4 (Web Text))

Max Activating Token Index: 510

Text #9

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.3950. Min Act: -0.0002

Data Index: 763916 (C4 (Web Text))

Max Activating Token Index: 32

Text #10

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.3615. Min Act: -0.0002

Data Index: 1086966 (C4 (Web Text))

Max Activating Token Index: 164

Text #11

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.3266. Min Act: -0.0002

Data Index: 939619 (C4 (Web Text))

Max Activating Token Index: 326

Text #12

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.3476. Min Act: -0.0002

Data Index: 318534 (C4 (Web Text))

Max Activating Token Index: 113

Text #13

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.3310. Min Act: -0.0002

Data Index: 1506299 (Python Code)

Max Activating Token Index: 709

Text #14

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.2950. Min Act: -0.0002

Data Index: 1300964 (C4 (Web Text))

Max Activating Token Index: 482

Text #15

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.2701. Min Act: -0.0002

Data Index: 169654 (C4 (Web Text))

Max Activating Token Index: 131

Text #16

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.2964. Min Act: -0.0002

Data Index: 391847 (C4 (Web Text))

Max Activating Token Index: 33

Text #17

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.2592. Min Act: -0.0002

Data Index: 1458576 (Python Code)

Max Activating Token Index: 184

Text #18

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.2846. Min Act: -0.0002

Data Index: 809188 (C4 (Web Text))

Max Activating Token Index: 709

Text #19

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.2599. Min Act: -0.0003

Data Index: 1124190 (C4 (Web Text))

Max Activating Token Index: 184