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

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

Neuron 2190 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3105. Min Range: -0.3105

Max Act: 0.3007. Min Act: -0.0000

Data Index: 991985 (C4 (Web Text))

Max Activating Token Index: 375

Text #1

Max Range: 0.3105. Min Range: -0.3105

Max Act: 0.3105. Min Act: -0.0000

Data Index: 57268 (C4 (Web Text))

Max Activating Token Index: 931

Text #2

Max Range: 0.3105. Min Range: -0.3105

Max Act: 0.2649. Min Act: -0.0000

Data Index: 410551 (C4 (Web Text))

Max Activating Token Index: 317

Text #3

Max Range: 0.3105. Min Range: -0.3105

Max Act: 0.2593. Min Act: -0.0001

Data Index: 301010 (C4 (Web Text))

Max Activating Token Index: 50

Text #4

Max Range: 0.3105. Min Range: -0.3105

Max Act: 0.2622. Min Act: -0.0000

Data Index: 205875 (C4 (Web Text))

Max Activating Token Index: 408

Text #5

Max Range: 0.3105. Min Range: -0.3105

Max Act: 0.2604. Min Act: -0.0000

Data Index: 482061 (C4 (Web Text))

Max Activating Token Index: 645

Text #6

Max Range: 0.3105. Min Range: -0.3105

Max Act: 0.2594. Min Act: -0.0001

Data Index: 1347808 (C4 (Web Text))

Max Activating Token Index: 231

Text #7

Max Range: 0.3105. Min Range: -0.3105

Max Act: 0.2679. Min Act: -0.0001

Data Index: 489597 (C4 (Web Text))

Max Activating Token Index: 446

Text #8

Max Range: 0.3105. Min Range: -0.3105

Max Act: 0.2505. Min Act: -0.0001

Data Index: 144797 (C4 (Web Text))

Max Activating Token Index: 615

Text #9

Max Range: 0.3105. Min Range: -0.3105

Max Act: 0.2483. Min Act: 0.0000

Data Index: 734339 (C4 (Web Text))

Max Activating Token Index: 423

Text #10

Max Range: 0.3105. Min Range: -0.3105

Max Act: 0.2437. Min Act: -0.0000

Data Index: 538964 (C4 (Web Text))

Max Activating Token Index: 213

Text #11

Max Range: 0.3105. Min Range: -0.3105

Max Act: 0.2538. Min Act: -0.0000

Data Index: 658940 (C4 (Web Text))

Max Activating Token Index: 786

Text #12

Max Range: 0.3105. Min Range: -0.3105

Max Act: 0.2553. Min Act: -0.0000

Data Index: 426577 (C4 (Web Text))

Max Activating Token Index: 150

Text #13

Max Range: 0.3105. Min Range: -0.3105

Max Act: 0.2451. Min Act: -0.0000

Data Index: 568494 (C4 (Web Text))

Max Activating Token Index: 499

Text #14

Max Range: 0.3105. Min Range: -0.3105

Max Act: 0.2502. Min Act: -0.0000

Data Index: 586293 (C4 (Web Text))

Max Activating Token Index: 505

Text #15

Max Range: 0.3105. Min Range: -0.3105

Max Act: 0.2429. Min Act: 0.0000

Data Index: 1139918 (C4 (Web Text))

Max Activating Token Index: 819

Text #16

Max Range: 0.3105. Min Range: -0.3105

Max Act: 0.2353. Min Act: -0.0000

Data Index: 1347244 (C4 (Web Text))

Max Activating Token Index: 197

Text #17

Max Range: 0.3105. Min Range: -0.3105

Max Act: 0.2331. Min Act: -0.0000

Data Index: 657459 (C4 (Web Text))

Max Activating Token Index: 521

Text #18

Max Range: 0.3105. Min Range: -0.3105

Max Act: 0.2339. Min Act: -0.0000

Data Index: 1552 (C4 (Web Text))

Max Activating Token Index: 100

Text #19

Max Range: 0.3105. Min Range: -0.3105

Max Act: 0.2274. Min Act: -0.0000

Data Index: 646214 (C4 (Web Text))

Max Activating Token Index: 286