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

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

Neuron 5594 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3584. Min Range: -1.3584

Max Act: 1.3584. Min Act: -0.0000

Data Index: 1000682 (C4 (Web Text))

Max Activating Token Index: 251

Text #1

Max Range: 1.3584. Min Range: -1.3584

Max Act: 1.1869. Min Act: -0.0000

Data Index: 272386 (C4 (Web Text))

Max Activating Token Index: 962

Text #2

Max Range: 1.3584. Min Range: -1.3584

Max Act: 0.9860. Min Act: -0.0000

Data Index: 227412 (C4 (Web Text))

Max Activating Token Index: 604

Text #3

Max Range: 1.3584. Min Range: -1.3584

Max Act: 1.0725. Min Act: -0.0000

Data Index: 139180 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 1.3584. Min Range: -1.3584

Max Act: 1.0535. Min Act: -0.0000

Data Index: 987331 (C4 (Web Text))

Max Activating Token Index: 998

Text #5

Max Range: 1.3584. Min Range: -1.3584

Max Act: 1.0240. Min Act: -0.0000

Data Index: 906146 (C4 (Web Text))

Max Activating Token Index: 547

Text #6

Max Range: 1.3584. Min Range: -1.3584

Max Act: 0.9742. Min Act: -0.0000

Data Index: 12481 (C4 (Web Text))

Max Activating Token Index: 511

Text #7

Max Range: 1.3584. Min Range: -1.3584

Max Act: 0.9950. Min Act: -0.0000

Data Index: 305147 (C4 (Web Text))

Max Activating Token Index: 425

Text #8

Max Range: 1.3584. Min Range: -1.3584

Max Act: 0.9942. Min Act: -0.0000

Data Index: 147510 (C4 (Web Text))

Max Activating Token Index: 98

Text #9

Max Range: 1.3584. Min Range: -1.3584

Max Act: 0.9847. Min Act: -0.0000

Data Index: 36058 (C4 (Web Text))

Max Activating Token Index: 211

Text #10

Max Range: 1.3584. Min Range: -1.3584

Max Act: 0.9258. Min Act: -0.0000

Data Index: 628000 (C4 (Web Text))

Max Activating Token Index: 819

Text #11

Max Range: 1.3584. Min Range: -1.3584

Max Act: 0.9660. Min Act: -0.0000

Data Index: 111165 (C4 (Web Text))

Max Activating Token Index: 431

Text #12

Max Range: 1.3584. Min Range: -1.3584

Max Act: 0.9409. Min Act: -0.0000

Data Index: 1107299 (C4 (Web Text))

Max Activating Token Index: 415

Text #13

Max Range: 1.3584. Min Range: -1.3584

Max Act: 0.9757. Min Act: -0.0000

Data Index: 425902 (C4 (Web Text))

Max Activating Token Index: 626

Text #14

Max Range: 1.3584. Min Range: -1.3584

Max Act: 0.9384. Min Act: -0.0000

Data Index: 346072 (C4 (Web Text))

Max Activating Token Index: 959

Text #15

Max Range: 1.3584. Min Range: -1.3584

Max Act: 0.9424. Min Act: -0.0000

Data Index: 1127403 (C4 (Web Text))

Max Activating Token Index: 725

Text #16

Max Range: 1.3584. Min Range: -1.3584

Max Act: 0.8536. Min Act: -0.0000

Data Index: 316108 (C4 (Web Text))

Max Activating Token Index: 434

Text #17

Max Range: 1.3584. Min Range: -1.3584

Max Act: 0.8514. Min Act: -0.0000

Data Index: 258107 (C4 (Web Text))

Max Activating Token Index: 645

Text #18

Max Range: 1.3584. Min Range: -1.3584

Max Act: 0.8804. Min Act: -0.0000

Data Index: 743500 (C4 (Web Text))

Max Activating Token Index: 474

Text #19

Max Range: 1.3584. Min Range: -1.3584

Max Act: 0.8330. Min Act: -0.0000

Data Index: 798498 (C4 (Web Text))

Max Activating Token Index: 623