Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1504 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0489. Min Act: -0.0001

Data Index: 1329999 (C4 (Web Text))

Max Activating Token Index: 251

Text #1

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0425. Min Act: -0.0001

Data Index: 524087 (C4 (Web Text))

Max Activating Token Index: 534

Text #2

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0406. Min Act: -0.0001

Data Index: 1091545 (C4 (Web Text))

Max Activating Token Index: 757

Text #3

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0431. Min Act: -0.0001

Data Index: 368204 (C4 (Web Text))

Max Activating Token Index: 841

Text #4

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0427. Min Act: -0.0001

Data Index: 1490800 (Python Code)

Max Activating Token Index: 212

Text #5

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0364. Min Act: -0.0001

Data Index: 364467 (C4 (Web Text))

Max Activating Token Index: 967

Text #6

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0369. Min Act: -0.0001

Data Index: 968416 (C4 (Web Text))

Max Activating Token Index: 59

Text #7

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0362. Min Act: -0.0001

Data Index: 1061496 (C4 (Web Text))

Max Activating Token Index: 865

Text #8

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0352. Min Act: -0.0001

Data Index: 492090 (C4 (Web Text))

Max Activating Token Index: 661

Text #9

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0336. Min Act: -0.0001

Data Index: 963494 (C4 (Web Text))

Max Activating Token Index: 673

Text #10

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0338. Min Act: -0.0001

Data Index: 359211 (C4 (Web Text))

Max Activating Token Index: 415

Text #11

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0334. Min Act: -0.0001

Data Index: 32850 (C4 (Web Text))

Max Activating Token Index: 601

Text #12

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0309. Min Act: -0.0001

Data Index: 23614 (C4 (Web Text))

Max Activating Token Index: 969

Text #13

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0294. Min Act: -0.0001

Data Index: 603845 (C4 (Web Text))

Max Activating Token Index: 939

Text #14

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0324. Min Act: -0.0001

Data Index: 806722 (C4 (Web Text))

Max Activating Token Index: 385

Text #15

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0325. Min Act: -0.0001

Data Index: 372159 (C4 (Web Text))

Max Activating Token Index: 844

Text #16

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0303. Min Act: -0.0001

Data Index: 1023602 (C4 (Web Text))

Max Activating Token Index: 672

Text #17

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0333. Min Act: -0.0001

Data Index: 1653900 (Python Code)

Max Activating Token Index: 227

Text #18

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0330. Min Act: -0.0001

Data Index: 487108 (C4 (Web Text))

Max Activating Token Index: 38

Text #19

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0309. Min Act: -0.0001

Data Index: 1495109 (Python Code)

Max Activating Token Index: 971