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

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

Neuron 2524 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9415. Min Range: -0.9415

Max Act: 0.9153. Min Act: -0.0000

Data Index: 1182487 (C4 (Web Text))

Max Activating Token Index: 847

Text #1

Max Range: 0.9415. Min Range: -0.9415

Max Act: 0.9415. Min Act: -0.0000

Data Index: 454038 (C4 (Web Text))

Max Activating Token Index: 524

Text #2

Max Range: 0.9415. Min Range: -0.9415

Max Act: 0.8607. Min Act: -0.0000

Data Index: 743374 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 0.9415. Min Range: -0.9415

Max Act: 0.8764. Min Act: -0.0000

Data Index: 557550 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 0.9415. Min Range: -0.9415

Max Act: 0.7735. Min Act: -0.0000

Data Index: 1162624 (C4 (Web Text))

Max Activating Token Index: 186

Text #5

Max Range: 0.9415. Min Range: -0.9415

Max Act: 0.7182. Min Act: -0.0000

Data Index: 1107417 (C4 (Web Text))

Max Activating Token Index: 380

Text #6

Max Range: 0.9415. Min Range: -0.9415

Max Act: 0.6835. Min Act: -0.0000

Data Index: 1035811 (C4 (Web Text))

Max Activating Token Index: 161

Text #7

Max Range: 0.9415. Min Range: -0.9415

Max Act: 0.7206. Min Act: -0.0000

Data Index: 95880 (C4 (Web Text))

Max Activating Token Index: 611

Text #8

Max Range: 0.9415. Min Range: -0.9415

Max Act: 0.7593. Min Act: -0.0000

Data Index: 890856 (C4 (Web Text))

Max Activating Token Index: 574

Text #9

Max Range: 0.9415. Min Range: -0.9415

Max Act: 0.7273. Min Act: -0.0000

Data Index: 1168904 (C4 (Web Text))

Max Activating Token Index: 757

Text #10

Max Range: 0.9415. Min Range: -0.9415

Max Act: 0.6677. Min Act: -0.0000

Data Index: 257757 (C4 (Web Text))

Max Activating Token Index: 788

Text #11

Max Range: 0.9415. Min Range: -0.9415

Max Act: 0.6452. Min Act: -0.0000

Data Index: 1264402 (C4 (Web Text))

Max Activating Token Index: 171

Text #12

Max Range: 0.9415. Min Range: -0.9415

Max Act: 0.6336. Min Act: -0.0000

Data Index: 660616 (C4 (Web Text))

Max Activating Token Index: 44

Text #13

Max Range: 0.9415. Min Range: -0.9415

Max Act: 0.6347. Min Act: -0.0000

Data Index: 1037223 (C4 (Web Text))

Max Activating Token Index: 609

Text #14

Max Range: 0.9415. Min Range: -0.9415

Max Act: 0.5971. Min Act: -0.0000

Data Index: 1043711 (C4 (Web Text))

Max Activating Token Index: 263

Text #15

Max Range: 0.9415. Min Range: -0.9415

Max Act: 0.5969. Min Act: -0.0000

Data Index: 247753 (C4 (Web Text))

Max Activating Token Index: 920

Text #16

Max Range: 0.9415. Min Range: -0.9415

Max Act: 0.5748. Min Act: -0.0000

Data Index: 371303 (C4 (Web Text))

Max Activating Token Index: 594

Text #17

Max Range: 0.9415. Min Range: -0.9415

Max Act: 0.5796. Min Act: -0.0000

Data Index: 992691 (C4 (Web Text))

Max Activating Token Index: 584

Text #18

Max Range: 0.9415. Min Range: -0.9415

Max Act: 0.5763. Min Act: -0.0000

Data Index: 1228639 (C4 (Web Text))

Max Activating Token Index: 584

Text #19

Max Range: 0.9415. Min Range: -0.9415

Max Act: 0.5939. Min Act: -0.0000

Data Index: 786072 (C4 (Web Text))

Max Activating Token Index: 596