Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2637 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3643. Min Range: -1.3643

Max Act: 1.3643. Min Act: -0.0000

Data Index: 13836 (C4 (Web Text))

Max Activating Token Index: 559

Text #1

Max Range: 1.3643. Min Range: -1.3643

Max Act: 1.2139. Min Act: -0.0000

Data Index: 638974 (C4 (Web Text))

Max Activating Token Index: 164

Text #2

Max Range: 1.3643. Min Range: -1.3643

Max Act: 1.1009. Min Act: -0.0000

Data Index: 785695 (C4 (Web Text))

Max Activating Token Index: 369

Text #3

Max Range: 1.3643. Min Range: -1.3643

Max Act: 1.0653. Min Act: -0.0000

Data Index: 1104493 (C4 (Web Text))

Max Activating Token Index: 52

Text #4

Max Range: 1.3643. Min Range: -1.3643

Max Act: 0.9968. Min Act: -0.0000

Data Index: 867455 (C4 (Web Text))

Max Activating Token Index: 778

Text #5

Max Range: 1.3643. Min Range: -1.3643

Max Act: 0.9494. Min Act: -0.0000

Data Index: 1051741 (C4 (Web Text))

Max Activating Token Index: 188

Text #6

Max Range: 1.3643. Min Range: -1.3643

Max Act: 1.0085. Min Act: -0.0000

Data Index: 681409 (C4 (Web Text))

Max Activating Token Index: 404

Text #7

Max Range: 1.3643. Min Range: -1.3643

Max Act: 0.9576. Min Act: -0.0000

Data Index: 549177 (C4 (Web Text))

Max Activating Token Index: 548

Text #8

Max Range: 1.3643. Min Range: -1.3643

Max Act: 0.9688. Min Act: -0.0000

Data Index: 1304268 (C4 (Web Text))

Max Activating Token Index: 451

Text #9

Max Range: 1.3643. Min Range: -1.3643

Max Act: 0.9328. Min Act: -0.0000

Data Index: 15177 (C4 (Web Text))

Max Activating Token Index: 302

Text #10

Max Range: 1.3643. Min Range: -1.3643

Max Act: 0.8710. Min Act: -0.0000

Data Index: 646521 (C4 (Web Text))

Max Activating Token Index: 688

Text #11

Max Range: 1.3643. Min Range: -1.3643

Max Act: 0.9436. Min Act: -0.0000

Data Index: 1308930 (C4 (Web Text))

Max Activating Token Index: 955

Text #12

Max Range: 1.3643. Min Range: -1.3643

Max Act: 0.9047. Min Act: -0.0000

Data Index: 10510 (C4 (Web Text))

Max Activating Token Index: 519

Text #13

Max Range: 1.3643. Min Range: -1.3643

Max Act: 0.8659. Min Act: -0.0000

Data Index: 313297 (C4 (Web Text))

Max Activating Token Index: 582

Text #14

Max Range: 1.3643. Min Range: -1.3643

Max Act: 0.8337. Min Act: -0.0000

Data Index: 555748 (C4 (Web Text))

Max Activating Token Index: 218

Text #15

Max Range: 1.3643. Min Range: -1.3643

Max Act: 0.8981. Min Act: -0.0000

Data Index: 919559 (C4 (Web Text))

Max Activating Token Index: 58

Text #16

Max Range: 1.3643. Min Range: -1.3643

Max Act: 0.8425. Min Act: -0.0000

Data Index: 717027 (C4 (Web Text))

Max Activating Token Index: 348

Text #17

Max Range: 1.3643. Min Range: -1.3643

Max Act: 0.8416. Min Act: -0.0000

Data Index: 1122958 (C4 (Web Text))

Max Activating Token Index: 311

Text #18

Max Range: 1.3643. Min Range: -1.3643

Max Act: 0.8833. Min Act: -0.0000

Data Index: 497753 (C4 (Web Text))

Max Activating Token Index: 641

Text #19

Max Range: 1.3643. Min Range: -1.3643

Max Act: 0.8022. Min Act: -0.0000

Data Index: 445685 (C4 (Web Text))

Max Activating Token Index: 398