Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 849 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7409. Min Range: -0.7409

Max Act: 0.7325. Min Act: -0.0001

Data Index: 1041657 (C4 (Web Text))

Max Activating Token Index: 345

Text #1

Max Range: 0.7409. Min Range: -0.7409

Max Act: 0.7327. Min Act: -0.0001

Data Index: 949240 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.7409. Min Range: -0.7409

Max Act: 0.7409. Min Act: -0.0001

Data Index: 999778 (C4 (Web Text))

Max Activating Token Index: 882

Text #3

Max Range: 0.7409. Min Range: -0.7409

Max Act: 0.7111. Min Act: -0.0001

Data Index: 432057 (C4 (Web Text))

Max Activating Token Index: 155

Text #4

Max Range: 0.7409. Min Range: -0.7409

Max Act: 0.6839. Min Act: -0.0001

Data Index: 986118 (C4 (Web Text))

Max Activating Token Index: 489

Text #5

Max Range: 0.7409. Min Range: -0.7409

Max Act: 0.6572. Min Act: -0.0000

Data Index: 720629 (C4 (Web Text))

Max Activating Token Index: 68

Text #6

Max Range: 0.7409. Min Range: -0.7409

Max Act: 0.6509. Min Act: -0.0001

Data Index: 1302057 (C4 (Web Text))

Max Activating Token Index: 292

Text #7

Max Range: 0.7409. Min Range: -0.7409

Max Act: 0.6961. Min Act: -0.0001

Data Index: 877585 (C4 (Web Text))

Max Activating Token Index: 640

Text #8

Max Range: 0.7409. Min Range: -0.7409

Max Act: 0.6268. Min Act: -0.0001

Data Index: 944034 (C4 (Web Text))

Max Activating Token Index: 144

Text #9

Max Range: 0.7409. Min Range: -0.7409

Max Act: 0.6810. Min Act: -0.0001

Data Index: 1012449 (C4 (Web Text))

Max Activating Token Index: 449

Text #10

Max Range: 0.7409. Min Range: -0.7409

Max Act: 0.6558. Min Act: -0.0000

Data Index: 332131 (C4 (Web Text))

Max Activating Token Index: 466

Text #11

Max Range: 0.7409. Min Range: -0.7409

Max Act: 0.6786. Min Act: -0.0000

Data Index: 347206 (C4 (Web Text))

Max Activating Token Index: 552

Text #12

Max Range: 0.7409. Min Range: -0.7409

Max Act: 0.6363. Min Act: -0.0001

Data Index: 1329574 (C4 (Web Text))

Max Activating Token Index: 497

Text #13

Max Range: 0.7409. Min Range: -0.7409

Max Act: 0.6695. Min Act: -0.0001

Data Index: 126063 (C4 (Web Text))

Max Activating Token Index: 71

Text #14

Max Range: 0.7409. Min Range: -0.7409

Max Act: 0.6444. Min Act: -0.0001

Data Index: 937431 (C4 (Web Text))

Max Activating Token Index: 101

Text #15

Max Range: 0.7409. Min Range: -0.7409

Max Act: 0.6644. Min Act: -0.0000

Data Index: 92650 (C4 (Web Text))

Max Activating Token Index: 929

Text #16

Max Range: 0.7409. Min Range: -0.7409

Max Act: 0.6167. Min Act: -0.0001

Data Index: 436599 (C4 (Web Text))

Max Activating Token Index: 570

Text #17

Max Range: 0.7409. Min Range: -0.7409

Max Act: 0.6130. Min Act: -0.0000

Data Index: 320285 (C4 (Web Text))

Max Activating Token Index: 555

Text #18

Max Range: 0.7409. Min Range: -0.7409

Max Act: 0.6278. Min Act: -0.0001

Data Index: 855588 (C4 (Web Text))

Max Activating Token Index: 574

Text #19

Max Range: 0.7409. Min Range: -0.7409

Max Act: 0.5913. Min Act: -0.0000

Data Index: 63599 (C4 (Web Text))

Max Activating Token Index: 422