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

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

Neuron 601 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: 0.3137. Min Range: -0.3137

Max Act: 0.3137. Min Act: -0.0001

Data Index: 224986 (C4 (Web Text))

Max Activating Token Index: 555

Text #1

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2977. Min Act: -0.0001

Data Index: 304131 (C4 (Web Text))

Max Activating Token Index: 685

Text #2

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2746. Min Act: -0.0000

Data Index: 732411 (C4 (Web Text))

Max Activating Token Index: 722

Text #3

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2708. Min Act: -0.0001

Data Index: 872879 (C4 (Web Text))

Max Activating Token Index: 508

Text #4

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2584. Min Act: -0.0000

Data Index: 544347 (C4 (Web Text))

Max Activating Token Index: 278

Text #5

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2542. Min Act: -0.0001

Data Index: 614262 (C4 (Web Text))

Max Activating Token Index: 148

Text #6

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2526. Min Act: -0.0000

Data Index: 776978 (C4 (Web Text))

Max Activating Token Index: 842

Text #7

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2448. Min Act: -0.0001

Data Index: 524600 (C4 (Web Text))

Max Activating Token Index: 861

Text #8

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2577. Min Act: -0.0000

Data Index: 503290 (C4 (Web Text))

Max Activating Token Index: 860

Text #9

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2376. Min Act: -0.0001

Data Index: 1317585 (C4 (Web Text))

Max Activating Token Index: 165

Text #10

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2472. Min Act: -0.0000

Data Index: 332118 (C4 (Web Text))

Max Activating Token Index: 467

Text #11

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2425. Min Act: -0.0001

Data Index: 857233 (C4 (Web Text))

Max Activating Token Index: 209

Text #12

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2369. Min Act: -0.0000

Data Index: 151211 (C4 (Web Text))

Max Activating Token Index: 247

Text #13

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2384. Min Act: -0.0001

Data Index: 624739 (C4 (Web Text))

Max Activating Token Index: 50

Text #14

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2479. Min Act: -0.0001

Data Index: 512963 (C4 (Web Text))

Max Activating Token Index: 104

Text #15

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2489. Min Act: -0.0000

Data Index: 1099366 (C4 (Web Text))

Max Activating Token Index: 294

Text #16

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2382. Min Act: -0.0000

Data Index: 1217257 (C4 (Web Text))

Max Activating Token Index: 382

Text #17

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2435. Min Act: -0.0001

Data Index: 1416521 (Python Code)

Max Activating Token Index: 109

Text #18

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2232. Min Act: -0.0000

Data Index: 73223 (C4 (Web Text))

Max Activating Token Index: 903

Text #19

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2197. Min Act: -0.0000

Data Index: 829081 (C4 (Web Text))

Max Activating Token Index: 863