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

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

Neuron 3111 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0618. Min Act: -0.0002

Data Index: 1309923 (C4 (Web Text))

Max Activating Token Index: 207

Text #1

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0447. Min Act: -0.0002

Data Index: 467765 (C4 (Web Text))

Max Activating Token Index: 281

Text #2

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0485. Min Act: -0.0002

Data Index: 500873 (C4 (Web Text))

Max Activating Token Index: 384

Text #3

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0483. Min Act: -0.0002

Data Index: 417455 (C4 (Web Text))

Max Activating Token Index: 584

Text #4

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0497. Min Act: -0.0002

Data Index: 206335 (C4 (Web Text))

Max Activating Token Index: 152

Text #5

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0459. Min Act: -0.0002

Data Index: 268663 (C4 (Web Text))

Max Activating Token Index: 595

Text #6

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0495. Min Act: -0.0002

Data Index: 171961 (C4 (Web Text))

Max Activating Token Index: 415

Text #7

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0453. Min Act: -0.0002

Data Index: 1305666 (C4 (Web Text))

Max Activating Token Index: 267

Text #8

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0416. Min Act: -0.0002

Data Index: 1149984 (C4 (Web Text))

Max Activating Token Index: 151

Text #9

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0444. Min Act: -0.0002

Data Index: 1188674 (C4 (Web Text))

Max Activating Token Index: 557

Text #10

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0446. Min Act: -0.0002

Data Index: 325334 (C4 (Web Text))

Max Activating Token Index: 802

Text #11

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0425. Min Act: -0.0002

Data Index: 912047 (C4 (Web Text))

Max Activating Token Index: 349

Text #12

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0435. Min Act: -0.0002

Data Index: 381057 (C4 (Web Text))

Max Activating Token Index: 544

Text #13

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0464. Min Act: -0.0002

Data Index: 414182 (C4 (Web Text))

Max Activating Token Index: 224

Text #14

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0383. Min Act: -0.0002

Data Index: 980733 (C4 (Web Text))

Max Activating Token Index: 312

Text #15

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0455. Min Act: -0.0002

Data Index: 395651 (C4 (Web Text))

Max Activating Token Index: 236

Text #16

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0445. Min Act: -0.0002

Data Index: 783146 (C4 (Web Text))

Max Activating Token Index: 767

Text #17

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0461. Min Act: -0.0002

Data Index: 529538 (C4 (Web Text))

Max Activating Token Index: 690

Text #18

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0557. Min Act: -0.0002

Data Index: 122481 (C4 (Web Text))

Max Activating Token Index: 311

Text #19

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0425. Min Act: -0.0002

Data Index: 169345 (C4 (Web Text))

Max Activating Token Index: 613