Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 645 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.9969. Min Range: -0.9969

Max Act: 0.9232. Min Act: -0.0001

Data Index: 284229 (C4 (Web Text))

Max Activating Token Index: 994

Text #1

Max Range: 0.9969. Min Range: -0.9969

Max Act: 0.9969. Min Act: -0.0001

Data Index: 330783 (C4 (Web Text))

Max Activating Token Index: 182

Text #2

Max Range: 0.9969. Min Range: -0.9969

Max Act: 0.9344. Min Act: -0.0001

Data Index: 287751 (C4 (Web Text))

Max Activating Token Index: 808

Text #3

Max Range: 0.9969. Min Range: -0.9969

Max Act: 0.9945. Min Act: -0.0001

Data Index: 974345 (C4 (Web Text))

Max Activating Token Index: 853

Text #4

Max Range: 0.9969. Min Range: -0.9969

Max Act: 0.9884. Min Act: -0.0001

Data Index: 262482 (C4 (Web Text))

Max Activating Token Index: 196

Text #5

Max Range: 0.9969. Min Range: -0.9969

Max Act: 0.8835. Min Act: -0.0001

Data Index: 274713 (C4 (Web Text))

Max Activating Token Index: 940

Text #6

Max Range: 0.9969. Min Range: -0.9969

Max Act: 0.8428. Min Act: -0.0001

Data Index: 609094 (C4 (Web Text))

Max Activating Token Index: 220

Text #7

Max Range: 0.9969. Min Range: -0.9969

Max Act: 0.8610. Min Act: -0.0001

Data Index: 158548 (C4 (Web Text))

Max Activating Token Index: 521

Text #8

Max Range: 0.9969. Min Range: -0.9969

Max Act: 0.9020. Min Act: -0.0001

Data Index: 137913 (C4 (Web Text))

Max Activating Token Index: 884

Text #9

Max Range: 0.9969. Min Range: -0.9969

Max Act: 0.8583. Min Act: -0.0001

Data Index: 52640 (C4 (Web Text))

Max Activating Token Index: 383

Text #10

Max Range: 0.9969. Min Range: -0.9969

Max Act: 0.7348. Min Act: -0.0001

Data Index: 822455 (C4 (Web Text))

Max Activating Token Index: 344

Text #11

Max Range: 0.9969. Min Range: -0.9969

Max Act: 0.8201. Min Act: -0.0001

Data Index: 1258581 (C4 (Web Text))

Max Activating Token Index: 882

Text #12

Max Range: 0.9969. Min Range: -0.9969

Max Act: 0.8566. Min Act: -0.0001

Data Index: 200757 (C4 (Web Text))

Max Activating Token Index: 912

Text #13

Max Range: 0.9969. Min Range: -0.9969

Max Act: 0.8305. Min Act: -0.0001

Data Index: 85693 (C4 (Web Text))

Max Activating Token Index: 719

Text #14

Max Range: 0.9969. Min Range: -0.9969

Max Act: 0.8177. Min Act: -0.0001

Data Index: 44658 (C4 (Web Text))

Max Activating Token Index: 776

Text #15

Max Range: 0.9969. Min Range: -0.9969

Max Act: 0.8439. Min Act: -0.0001

Data Index: 56709 (C4 (Web Text))

Max Activating Token Index: 91

Text #16

Max Range: 0.9969. Min Range: -0.9969

Max Act: 0.7810. Min Act: -0.0001

Data Index: 665421 (C4 (Web Text))

Max Activating Token Index: 459

Text #17

Max Range: 0.9969. Min Range: -0.9969

Max Act: 0.8316. Min Act: -0.0001

Data Index: 1043648 (C4 (Web Text))

Max Activating Token Index: 191

Text #18

Max Range: 0.9969. Min Range: -0.9969

Max Act: 0.8043. Min Act: -0.0001

Data Index: 739040 (C4 (Web Text))

Max Activating Token Index: 187

Text #19

Max Range: 0.9969. Min Range: -0.9969

Max Act: 0.8000. Min Act: -0.0001

Data Index: 1091833 (C4 (Web Text))

Max Activating Token Index: 29