Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3458 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3435. Min Range: -0.3435

Max Act: 0.3332. Min Act: -0.0000

Data Index: 330190 (C4 (Web Text))

Max Activating Token Index: 53

Text #1

Max Range: 0.3435. Min Range: -0.3435

Max Act: 0.3435. Min Act: -0.0000

Data Index: 649540 (C4 (Web Text))

Max Activating Token Index: 641

Text #2

Max Range: 0.3435. Min Range: -0.3435

Max Act: 0.3125. Min Act: -0.0000

Data Index: 860807 (C4 (Web Text))

Max Activating Token Index: 726

Text #3

Max Range: 0.3435. Min Range: -0.3435

Max Act: 0.2906. Min Act: -0.0000

Data Index: 128228 (C4 (Web Text))

Max Activating Token Index: 460

Text #4

Max Range: 0.3435. Min Range: -0.3435

Max Act: 0.2984. Min Act: -0.0000

Data Index: 1336239 (C4 (Web Text))

Max Activating Token Index: 646

Text #5

Max Range: 0.3435. Min Range: -0.3435

Max Act: 0.2951. Min Act: -0.0000

Data Index: 395645 (C4 (Web Text))

Max Activating Token Index: 800

Text #6

Max Range: 0.3435. Min Range: -0.3435

Max Act: 0.2669. Min Act: -0.0000

Data Index: 1305752 (C4 (Web Text))

Max Activating Token Index: 331

Text #7

Max Range: 0.3435. Min Range: -0.3435

Max Act: 0.2706. Min Act: -0.0000

Data Index: 245339 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 0.3435. Min Range: -0.3435

Max Act: 0.2719. Min Act: -0.0000

Data Index: 384574 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 0.3435. Min Range: -0.3435

Max Act: 0.2368. Min Act: -0.0000

Data Index: 1205709 (C4 (Web Text))

Max Activating Token Index: 225

Text #10

Max Range: 0.3435. Min Range: -0.3435

Max Act: 0.2527. Min Act: -0.0000

Data Index: 41956 (C4 (Web Text))

Max Activating Token Index: 741

Text #11

Max Range: 0.3435. Min Range: -0.3435

Max Act: 0.2505. Min Act: -0.0000

Data Index: 251839 (C4 (Web Text))

Max Activating Token Index: 676

Text #12

Max Range: 0.3435. Min Range: -0.3435

Max Act: 0.2408. Min Act: -0.0000

Data Index: 816972 (C4 (Web Text))

Max Activating Token Index: 775

Text #13

Max Range: 0.3435. Min Range: -0.3435

Max Act: 0.2495. Min Act: -0.0000

Data Index: 788112 (C4 (Web Text))

Max Activating Token Index: 619

Text #14

Max Range: 0.3435. Min Range: -0.3435

Max Act: 0.2511. Min Act: -0.0000

Data Index: 1287025 (C4 (Web Text))

Max Activating Token Index: 576

Text #15

Max Range: 0.3435. Min Range: -0.3435

Max Act: 0.2431. Min Act: -0.0000

Data Index: 213934 (C4 (Web Text))

Max Activating Token Index: 733

Text #16

Max Range: 0.3435. Min Range: -0.3435

Max Act: 0.2295. Min Act: -0.0000

Data Index: 457215 (C4 (Web Text))

Max Activating Token Index: 232

Text #17

Max Range: 0.3435. Min Range: -0.3435

Max Act: 0.2372. Min Act: -0.0000

Data Index: 483237 (C4 (Web Text))

Max Activating Token Index: 576

Text #18

Max Range: 0.3435. Min Range: -0.3435

Max Act: 0.2427. Min Act: -0.0000

Data Index: 1290857 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 0.3435. Min Range: -0.3435

Max Act: 0.2208. Min Act: -0.0000

Data Index: 200620 (C4 (Web Text))

Max Activating Token Index: 765