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

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

Neuron 1529 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: 3.2942. Min Range: -3.2942

Max Act: 3.2942. Min Act: -0.0000

Data Index: 252205 (C4 (Web Text))

Max Activating Token Index: 546

Text #1

Max Range: 3.2942. Min Range: -3.2942

Max Act: 2.2497. Min Act: -0.0000

Data Index: 894044 (C4 (Web Text))

Max Activating Token Index: 328

Text #2

Max Range: 3.2942. Min Range: -3.2942

Max Act: 2.1319. Min Act: -0.0000

Data Index: 1161975 (C4 (Web Text))

Max Activating Token Index: 772

Text #3

Max Range: 3.2942. Min Range: -3.2942

Max Act: 2.1976. Min Act: -0.0000

Data Index: 929644 (C4 (Web Text))

Max Activating Token Index: 467

Text #4

Max Range: 3.2942. Min Range: -3.2942

Max Act: 1.9963. Min Act: -0.0000

Data Index: 120681 (C4 (Web Text))

Max Activating Token Index: 521

Text #5

Max Range: 3.2942. Min Range: -3.2942

Max Act: 1.8267. Min Act: -0.0000

Data Index: 896558 (C4 (Web Text))

Max Activating Token Index: 409

Text #6

Max Range: 3.2942. Min Range: -3.2942

Max Act: 1.7253. Min Act: -0.0000

Data Index: 9469 (C4 (Web Text))

Max Activating Token Index: 421

Text #7

Max Range: 3.2942. Min Range: -3.2942

Max Act: 1.7273. Min Act: -0.0000

Data Index: 816219 (C4 (Web Text))

Max Activating Token Index: 347

Text #8

Max Range: 3.2942. Min Range: -3.2942

Max Act: 1.5970. Min Act: -0.0000

Data Index: 79490 (C4 (Web Text))

Max Activating Token Index: 918

Text #9

Max Range: 3.2942. Min Range: -3.2942

Max Act: 1.6451. Min Act: -0.0000

Data Index: 188948 (C4 (Web Text))

Max Activating Token Index: 681

Text #10

Max Range: 3.2942. Min Range: -3.2942

Max Act: 1.6406. Min Act: -0.0000

Data Index: 323704 (C4 (Web Text))

Max Activating Token Index: 807

Text #11

Max Range: 3.2942. Min Range: -3.2942

Max Act: 1.6388. Min Act: -0.0000

Data Index: 124438 (C4 (Web Text))

Max Activating Token Index: 956

Text #12

Max Range: 3.2942. Min Range: -3.2942

Max Act: 1.6322. Min Act: -0.0000

Data Index: 1113988 (C4 (Web Text))

Max Activating Token Index: 718

Text #13

Max Range: 3.2942. Min Range: -3.2942

Max Act: 1.4903. Min Act: -0.0000

Data Index: 915580 (C4 (Web Text))

Max Activating Token Index: 798

Text #14

Max Range: 3.2942. Min Range: -3.2942

Max Act: 1.4426. Min Act: -0.0000

Data Index: 941586 (C4 (Web Text))

Max Activating Token Index: 143

Text #15

Max Range: 3.2942. Min Range: -3.2942

Max Act: 1.5368. Min Act: -0.0000

Data Index: 789397 (C4 (Web Text))

Max Activating Token Index: 575

Text #16

Max Range: 3.2942. Min Range: -3.2942

Max Act: 1.4885. Min Act: -0.0000

Data Index: 979978 (C4 (Web Text))

Max Activating Token Index: 963

Text #17

Max Range: 3.2942. Min Range: -3.2942

Max Act: 1.4688. Min Act: -0.0000

Data Index: 1084536 (C4 (Web Text))

Max Activating Token Index: 405

Text #18

Max Range: 3.2942. Min Range: -3.2942

Max Act: 1.2802. Min Act: -0.0000

Data Index: 941674 (C4 (Web Text))

Max Activating Token Index: 998

Text #19

Max Range: 3.2942. Min Range: -3.2942

Max Act: 1.4329. Min Act: -0.0000

Data Index: 610443 (C4 (Web Text))

Max Activating Token Index: 325