Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2376 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.9498. Min Range: -1.9498

Max Act: 1.9400. Min Act: -0.0003

Data Index: 1566914 (Python Code)

Max Activating Token Index: 871

Text #1

Max Range: 1.9498. Min Range: -1.9498

Max Act: 1.9494. Min Act: -0.0003

Data Index: 976033 (C4 (Web Text))

Max Activating Token Index: 633

Text #2

Max Range: 1.9498. Min Range: -1.9498

Max Act: 1.9498. Min Act: -0.0003

Data Index: 671619 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 1.9498. Min Range: -1.9498

Max Act: 1.8337. Min Act: -0.0003

Data Index: 732507 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 1.9498. Min Range: -1.9498

Max Act: 1.7062. Min Act: -0.0003

Data Index: 1051630 (C4 (Web Text))

Max Activating Token Index: 117

Text #5

Max Range: 1.9498. Min Range: -1.9498

Max Act: 1.7320. Min Act: -0.0003

Data Index: 839123 (C4 (Web Text))

Max Activating Token Index: 954

Text #6

Max Range: 1.9498. Min Range: -1.9498

Max Act: 1.6823. Min Act: -0.0003

Data Index: 687803 (C4 (Web Text))

Max Activating Token Index: 796

Text #7

Max Range: 1.9498. Min Range: -1.9498

Max Act: 1.6225. Min Act: -0.0003

Data Index: 1347513 (C4 (Web Text))

Max Activating Token Index: 652

Text #8

Max Range: 1.9498. Min Range: -1.9498

Max Act: 1.6287. Min Act: -0.0003

Data Index: 24856 (C4 (Web Text))

Max Activating Token Index: 403

Text #9

Max Range: 1.9498. Min Range: -1.9498

Max Act: 1.5994. Min Act: -0.0003

Data Index: 1209716 (C4 (Web Text))

Max Activating Token Index: 947

Text #10

Max Range: 1.9498. Min Range: -1.9498

Max Act: 1.4348. Min Act: -0.0003

Data Index: 1217793 (C4 (Web Text))

Max Activating Token Index: 808

Text #11

Max Range: 1.9498. Min Range: -1.9498

Max Act: 1.4336. Min Act: -0.0003

Data Index: 1656579 (Python Code)

Max Activating Token Index: 600

Text #12

Max Range: 1.9498. Min Range: -1.9498

Max Act: 1.5160. Min Act: -0.0003

Data Index: 623330 (C4 (Web Text))

Max Activating Token Index: 317

Text #13

Max Range: 1.9498. Min Range: -1.9498

Max Act: 1.5376. Min Act: -0.0003

Data Index: 386536 (C4 (Web Text))

Max Activating Token Index: 876

Text #14

Max Range: 1.9498. Min Range: -1.9498

Max Act: 1.4963. Min Act: -0.0003

Data Index: 554890 (C4 (Web Text))

Max Activating Token Index: 49

Text #15

Max Range: 1.9498. Min Range: -1.9498

Max Act: 1.5328. Min Act: -0.0003

Data Index: 1127735 (C4 (Web Text))

Max Activating Token Index: 89

Text #16

Max Range: 1.9498. Min Range: -1.9498

Max Act: 1.5684. Min Act: -0.0003

Data Index: 974422 (C4 (Web Text))

Max Activating Token Index: 327

Text #17

Max Range: 1.9498. Min Range: -1.9498

Max Act: 1.5149. Min Act: -0.0003

Data Index: 96436 (C4 (Web Text))

Max Activating Token Index: 218

Text #18

Max Range: 1.9498. Min Range: -1.9498

Max Act: 1.3564. Min Act: -0.0003

Data Index: 1196174 (C4 (Web Text))

Max Activating Token Index: 856

Text #19

Max Range: 1.9498. Min Range: -1.9498

Max Act: 1.4624. Min Act: -0.0003

Data Index: 100510 (C4 (Web Text))

Max Activating Token Index: 982