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

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

Neuron 3974 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: 0.4671. Min Range: -0.4671

Max Act: 0.4671. Min Act: -0.0001

Data Index: 17583 (C4 (Web Text))

Max Activating Token Index: 885

Text #1

Max Range: 0.4671. Min Range: -0.4671

Max Act: 0.4233. Min Act: -0.0000

Data Index: 496192 (C4 (Web Text))

Max Activating Token Index: 459

Text #2

Max Range: 0.4671. Min Range: -0.4671

Max Act: 0.4242. Min Act: -0.0000

Data Index: 410573 (C4 (Web Text))

Max Activating Token Index: 393

Text #3

Max Range: 0.4671. Min Range: -0.4671

Max Act: 0.3723. Min Act: -0.0000

Data Index: 707041 (C4 (Web Text))

Max Activating Token Index: 223

Text #4

Max Range: 0.4671. Min Range: -0.4671

Max Act: 0.3480. Min Act: -0.0000

Data Index: 1293909 (C4 (Web Text))

Max Activating Token Index: 503

Text #5

Max Range: 0.4671. Min Range: -0.4671

Max Act: 0.3439. Min Act: -0.0001

Data Index: 292856 (C4 (Web Text))

Max Activating Token Index: 40

Text #6

Max Range: 0.4671. Min Range: -0.4671

Max Act: 0.3323. Min Act: -0.0001

Data Index: 1281495 (C4 (Web Text))

Max Activating Token Index: 353

Text #7

Max Range: 0.4671. Min Range: -0.4671

Max Act: 0.3282. Min Act: -0.0001

Data Index: 1012420 (C4 (Web Text))

Max Activating Token Index: 353

Text #8

Max Range: 0.4671. Min Range: -0.4671

Max Act: 0.3255. Min Act: -0.0000

Data Index: 413384 (C4 (Web Text))

Max Activating Token Index: 1001

Text #9

Max Range: 0.4671. Min Range: -0.4671

Max Act: 0.3030. Min Act: -0.0000

Data Index: 273761 (C4 (Web Text))

Max Activating Token Index: 542

Text #10

Max Range: 0.4671. Min Range: -0.4671

Max Act: 0.3199. Min Act: -0.0000

Data Index: 1107103 (C4 (Web Text))

Max Activating Token Index: 999

Text #11

Max Range: 0.4671. Min Range: -0.4671

Max Act: 0.3184. Min Act: -0.0000

Data Index: 730886 (C4 (Web Text))

Max Activating Token Index: 794

Text #12

Max Range: 0.4671. Min Range: -0.4671

Max Act: 0.3009. Min Act: -0.0000

Data Index: 894604 (C4 (Web Text))

Max Activating Token Index: 504

Text #13

Max Range: 0.4671. Min Range: -0.4671

Max Act: 0.3095. Min Act: -0.0000

Data Index: 770352 (C4 (Web Text))

Max Activating Token Index: 586

Text #14

Max Range: 0.4671. Min Range: -0.4671

Max Act: 0.3008. Min Act: -0.0000

Data Index: 1083121 (C4 (Web Text))

Max Activating Token Index: 238

Text #15

Max Range: 0.4671. Min Range: -0.4671

Max Act: 0.3038. Min Act: -0.0000

Data Index: 661849 (C4 (Web Text))

Max Activating Token Index: 644

Text #16

Max Range: 0.4671. Min Range: -0.4671

Max Act: 0.2893. Min Act: -0.0000

Data Index: 165029 (C4 (Web Text))

Max Activating Token Index: 368

Text #17

Max Range: 0.4671. Min Range: -0.4671

Max Act: 0.3088. Min Act: -0.0000

Data Index: 930378 (C4 (Web Text))

Max Activating Token Index: 571

Text #18

Max Range: 0.4671. Min Range: -0.4671

Max Act: 0.2897. Min Act: -0.0000

Data Index: 593851 (C4 (Web Text))

Max Activating Token Index: 597

Text #19

Max Range: 0.4671. Min Range: -0.4671

Max Act: 0.2986. Min Act: -0.0000

Data Index: 1359654 (C4 (Web Text))

Max Activating Token Index: 913