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

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

Neuron 2306 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: 3.1724. Min Range: -3.1724

Max Act: 3.0174. Min Act: -0.0000

Data Index: 728473 (C4 (Web Text))

Max Activating Token Index: 957

Text #1

Max Range: 3.1724. Min Range: -3.1724

Max Act: 3.1724. Min Act: -0.0000

Data Index: 900391 (C4 (Web Text))

Max Activating Token Index: 831

Text #2

Max Range: 3.1724. Min Range: -3.1724

Max Act: 2.9748. Min Act: -0.0000

Data Index: 548394 (C4 (Web Text))

Max Activating Token Index: 686

Text #3

Max Range: 3.1724. Min Range: -3.1724

Max Act: 2.8441. Min Act: -0.0000

Data Index: 1100014 (C4 (Web Text))

Max Activating Token Index: 474

Text #4

Max Range: 3.1724. Min Range: -3.1724

Max Act: 2.6423. Min Act: -0.0000

Data Index: 1013950 (C4 (Web Text))

Max Activating Token Index: 371

Text #5

Max Range: 3.1724. Min Range: -3.1724

Max Act: 2.6864. Min Act: -0.0000

Data Index: 1118798 (C4 (Web Text))

Max Activating Token Index: 992

Text #6

Max Range: 3.1724. Min Range: -3.1724

Max Act: 2.6472. Min Act: -0.0000

Data Index: 398857 (C4 (Web Text))

Max Activating Token Index: 412

Text #7

Max Range: 3.1724. Min Range: -3.1724

Max Act: 2.5099. Min Act: -0.0000

Data Index: 955135 (C4 (Web Text))

Max Activating Token Index: 532

Text #8

Max Range: 3.1724. Min Range: -3.1724

Max Act: 2.4800. Min Act: -0.0000

Data Index: 165999 (C4 (Web Text))

Max Activating Token Index: 229

Text #9

Max Range: 3.1724. Min Range: -3.1724

Max Act: 2.4870. Min Act: -0.0000

Data Index: 865975 (C4 (Web Text))

Max Activating Token Index: 418

Text #10

Max Range: 3.1724. Min Range: -3.1724

Max Act: 2.5884. Min Act: -0.0000

Data Index: 1063091 (C4 (Web Text))

Max Activating Token Index: 506

Text #11

Max Range: 3.1724. Min Range: -3.1724

Max Act: 2.4591. Min Act: -0.0000

Data Index: 528582 (C4 (Web Text))

Max Activating Token Index: 682

Text #12

Max Range: 3.1724. Min Range: -3.1724

Max Act: 2.4382. Min Act: -0.0000

Data Index: 983367 (C4 (Web Text))

Max Activating Token Index: 895

Text #13

Max Range: 3.1724. Min Range: -3.1724

Max Act: 2.4175. Min Act: -0.0000

Data Index: 223204 (C4 (Web Text))

Max Activating Token Index: 580

Text #14

Max Range: 3.1724. Min Range: -3.1724

Max Act: 2.5493. Min Act: -0.0000

Data Index: 181583 (C4 (Web Text))

Max Activating Token Index: 435

Text #15

Max Range: 3.1724. Min Range: -3.1724

Max Act: 2.5369. Min Act: -0.0000

Data Index: 180773 (C4 (Web Text))

Max Activating Token Index: 668

Text #16

Max Range: 3.1724. Min Range: -3.1724

Max Act: 2.5273. Min Act: -0.0000

Data Index: 1601089 (Python Code)

Max Activating Token Index: 327

Text #17

Max Range: 3.1724. Min Range: -3.1724

Max Act: 2.6193. Min Act: -0.0000

Data Index: 328022 (C4 (Web Text))

Max Activating Token Index: 507

Text #18

Max Range: 3.1724. Min Range: -3.1724

Max Act: 2.5919. Min Act: -0.0000

Data Index: 1174197 (C4 (Web Text))

Max Activating Token Index: 947

Text #19

Max Range: 3.1724. Min Range: -3.1724

Max Act: 2.4582. Min Act: -0.0000

Data Index: 1011537 (C4 (Web Text))

Max Activating Token Index: 612