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

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

Neuron 3540 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.1802. Min Act: -0.0001

Data Index: 1113664 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 3.4315. Min Range: -3.4315

Max Act: 2.6051. Min Act: -0.0001

Data Index: 436222 (C4 (Web Text))

Max Activating Token Index: 258

Text #2

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.0349. Min Act: -0.0001

Data Index: 831282 (C4 (Web Text))

Max Activating Token Index: 620

Text #3

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.4315. Min Act: -0.0001

Data Index: 205518 (C4 (Web Text))

Max Activating Token Index: 608

Text #4

Max Range: 3.4315. Min Range: -3.4315

Max Act: 2.6954. Min Act: -0.0001

Data Index: 1075625 (C4 (Web Text))

Max Activating Token Index: 606

Text #5

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.1381. Min Act: -0.0001

Data Index: 443455 (C4 (Web Text))

Max Activating Token Index: 97

Text #6

Max Range: 3.4315. Min Range: -3.4315

Max Act: 2.7957. Min Act: -0.0001

Data Index: 425780 (C4 (Web Text))

Max Activating Token Index: 57

Text #7

Max Range: 3.4315. Min Range: -3.4315

Max Act: 2.9480. Min Act: -0.0001

Data Index: 90674 (C4 (Web Text))

Max Activating Token Index: 222

Text #8

Max Range: 3.4315. Min Range: -3.4315

Max Act: 2.8835. Min Act: -0.0001

Data Index: 663948 (C4 (Web Text))

Max Activating Token Index: 164

Text #9

Max Range: 3.4315. Min Range: -3.4315

Max Act: 2.9357. Min Act: -0.0001

Data Index: 1120037 (C4 (Web Text))

Max Activating Token Index: 814

Text #10

Max Range: 3.4315. Min Range: -3.4315

Max Act: 2.9623. Min Act: -0.0001

Data Index: 1033942 (C4 (Web Text))

Max Activating Token Index: 335

Text #11

Max Range: 3.4315. Min Range: -3.4315

Max Act: 2.7821. Min Act: -0.0001

Data Index: 711063 (C4 (Web Text))

Max Activating Token Index: 555

Text #12

Max Range: 3.4315. Min Range: -3.4315

Max Act: 2.8474. Min Act: -0.0001

Data Index: 120616 (C4 (Web Text))

Max Activating Token Index: 428

Text #13

Max Range: 3.4315. Min Range: -3.4315

Max Act: 2.9880. Min Act: -0.0001

Data Index: 16711 (C4 (Web Text))

Max Activating Token Index: 142

Text #14

Max Range: 3.4315. Min Range: -3.4315

Max Act: 2.7895. Min Act: -0.0001

Data Index: 801658 (C4 (Web Text))

Max Activating Token Index: 353

Text #15

Max Range: 3.4315. Min Range: -3.4315

Max Act: 2.6013. Min Act: -0.0001

Data Index: 355122 (C4 (Web Text))

Max Activating Token Index: 502

Text #16

Max Range: 3.4315. Min Range: -3.4315

Max Act: 2.6095. Min Act: -0.0001

Data Index: 440980 (C4 (Web Text))

Max Activating Token Index: 275

Text #17

Max Range: 3.4315. Min Range: -3.4315

Max Act: 2.6885. Min Act: -0.0001

Data Index: 634298 (C4 (Web Text))

Max Activating Token Index: 305

Text #18

Max Range: 3.4315. Min Range: -3.4315

Max Act: 2.9872. Min Act: -0.0001

Data Index: 383764 (C4 (Web Text))

Max Activating Token Index: 646

Text #19

Max Range: 3.4315. Min Range: -3.4315

Max Act: 2.5233. Min Act: -0.0001

Data Index: 848496 (C4 (Web Text))

Max Activating Token Index: 532