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

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

Neuron 5500 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1504. Min Range: -5.1504

Max Act: 5.1504. Min Act: -0.0000

Data Index: 802733 (C4 (Web Text))

Max Activating Token Index: 782

Text #1

Max Range: 5.1504. Min Range: -5.1504

Max Act: 4.9559. Min Act: -0.0000

Data Index: 556445 (C4 (Web Text))

Max Activating Token Index: 215

Text #2

Max Range: 5.1504. Min Range: -5.1504

Max Act: 4.9008. Min Act: -0.0000

Data Index: 94840 (C4 (Web Text))

Max Activating Token Index: 457

Text #3

Max Range: 5.1504. Min Range: -5.1504

Max Act: 4.6998. Min Act: -0.0000

Data Index: 536312 (C4 (Web Text))

Max Activating Token Index: 538

Text #4

Max Range: 5.1504. Min Range: -5.1504

Max Act: 4.6847. Min Act: -0.0000

Data Index: 232396 (C4 (Web Text))

Max Activating Token Index: 617

Text #5

Max Range: 5.1504. Min Range: -5.1504

Max Act: 4.8303. Min Act: -0.0000

Data Index: 348844 (C4 (Web Text))

Max Activating Token Index: 175

Text #6

Max Range: 5.1504. Min Range: -5.1504

Max Act: 4.5718. Min Act: -0.0000

Data Index: 334646 (C4 (Web Text))

Max Activating Token Index: 142

Text #7

Max Range: 5.1504. Min Range: -5.1504

Max Act: 4.5689. Min Act: -0.0000

Data Index: 1153004 (C4 (Web Text))

Max Activating Token Index: 521

Text #8

Max Range: 5.1504. Min Range: -5.1504

Max Act: 4.5530. Min Act: -0.0000

Data Index: 1281566 (C4 (Web Text))

Max Activating Token Index: 621

Text #9

Max Range: 5.1504. Min Range: -5.1504

Max Act: 4.7100. Min Act: -0.0000

Data Index: 1089350 (C4 (Web Text))

Max Activating Token Index: 782

Text #10

Max Range: 5.1504. Min Range: -5.1504

Max Act: 4.4837. Min Act: -0.0000

Data Index: 1273274 (C4 (Web Text))

Max Activating Token Index: 425

Text #11

Max Range: 5.1504. Min Range: -5.1504

Max Act: 4.4682. Min Act: -0.0000

Data Index: 1097405 (C4 (Web Text))

Max Activating Token Index: 419

Text #12

Max Range: 5.1504. Min Range: -5.1504

Max Act: 4.6360. Min Act: -0.0000

Data Index: 1002208 (C4 (Web Text))

Max Activating Token Index: 309

Text #13

Max Range: 5.1504. Min Range: -5.1504

Max Act: 4.4709. Min Act: -0.0000

Data Index: 598523 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 5.1504. Min Range: -5.1504

Max Act: 4.6378. Min Act: -0.0000

Data Index: 385537 (C4 (Web Text))

Max Activating Token Index: 333

Text #15

Max Range: 5.1504. Min Range: -5.1504

Max Act: 4.4459. Min Act: -0.0000

Data Index: 407932 (C4 (Web Text))

Max Activating Token Index: 89

Text #16

Max Range: 5.1504. Min Range: -5.1504

Max Act: 4.9847. Min Act: -0.0000

Data Index: 999578 (C4 (Web Text))

Max Activating Token Index: 332

Text #17

Max Range: 5.1504. Min Range: -5.1504

Max Act: 4.7849. Min Act: -0.0000

Data Index: 34798 (C4 (Web Text))

Max Activating Token Index: 703

Text #18

Max Range: 5.1504. Min Range: -5.1504

Max Act: 4.6039. Min Act: -0.0000

Data Index: 1114513 (C4 (Web Text))

Max Activating Token Index: 975

Text #19

Max Range: 5.1504. Min Range: -5.1504

Max Act: 4.4134. Min Act: -0.0000

Data Index: 308401 (C4 (Web Text))

Max Activating Token Index: 493