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

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

Neuron 1932 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2647. Min Range: -1.2647

Max Act: 1.2647. Min Act: -0.0000

Data Index: 1257690 (C4 (Web Text))

Max Activating Token Index: 222

Text #1

Max Range: 1.2647. Min Range: -1.2647

Max Act: 1.1004. Min Act: -0.0000

Data Index: 202839 (C4 (Web Text))

Max Activating Token Index: 831

Text #2

Max Range: 1.2647. Min Range: -1.2647

Max Act: 1.2140. Min Act: -0.0001

Data Index: 163778 (C4 (Web Text))

Max Activating Token Index: 21

Text #3

Max Range: 1.2647. Min Range: -1.2647

Max Act: 1.1278. Min Act: -0.0000

Data Index: 1111095 (C4 (Web Text))

Max Activating Token Index: 93

Text #4

Max Range: 1.2647. Min Range: -1.2647

Max Act: 1.0761. Min Act: -0.0000

Data Index: 433556 (C4 (Web Text))

Max Activating Token Index: 89

Text #5

Max Range: 1.2647. Min Range: -1.2647

Max Act: 1.0934. Min Act: -0.0001

Data Index: 346570 (C4 (Web Text))

Max Activating Token Index: 260

Text #6

Max Range: 1.2647. Min Range: -1.2647

Max Act: 1.0967. Min Act: -0.0000

Data Index: 1542083 (Python Code)

Max Activating Token Index: 75

Text #7

Max Range: 1.2647. Min Range: -1.2647

Max Act: 1.1223. Min Act: -0.0001

Data Index: 1329736 (C4 (Web Text))

Max Activating Token Index: 973

Text #8

Max Range: 1.2647. Min Range: -1.2647

Max Act: 1.0527. Min Act: -0.0001

Data Index: 51185 (C4 (Web Text))

Max Activating Token Index: 307

Text #9

Max Range: 1.2647. Min Range: -1.2647

Max Act: 1.0813. Min Act: -0.0001

Data Index: 1294229 (C4 (Web Text))

Max Activating Token Index: 10

Text #10

Max Range: 1.2647. Min Range: -1.2647

Max Act: 0.9661. Min Act: -0.0001

Data Index: 823378 (C4 (Web Text))

Max Activating Token Index: 216

Text #11

Max Range: 1.2647. Min Range: -1.2647

Max Act: 1.0020. Min Act: -0.0001

Data Index: 581878 (C4 (Web Text))

Max Activating Token Index: 843

Text #12

Max Range: 1.2647. Min Range: -1.2647

Max Act: 0.9900. Min Act: -0.0000

Data Index: 752328 (C4 (Web Text))

Max Activating Token Index: 87

Text #13

Max Range: 1.2647. Min Range: -1.2647

Max Act: 1.0891. Min Act: -0.0001

Data Index: 1045293 (C4 (Web Text))

Max Activating Token Index: 770

Text #14

Max Range: 1.2647. Min Range: -1.2647

Max Act: 0.9970. Min Act: -0.0001

Data Index: 937708 (C4 (Web Text))

Max Activating Token Index: 965

Text #15

Max Range: 1.2647. Min Range: -1.2647

Max Act: 1.0937. Min Act: -0.0000

Data Index: 253911 (C4 (Web Text))

Max Activating Token Index: 624

Text #16

Max Range: 1.2647. Min Range: -1.2647

Max Act: 1.0878. Min Act: -0.0000

Data Index: 464411 (C4 (Web Text))

Max Activating Token Index: 931

Text #17

Max Range: 1.2647. Min Range: -1.2647

Max Act: 1.0152. Min Act: -0.0000

Data Index: 303178 (C4 (Web Text))

Max Activating Token Index: 101

Text #18

Max Range: 1.2647. Min Range: -1.2647

Max Act: 1.0367. Min Act: -0.0000

Data Index: 145495 (C4 (Web Text))

Max Activating Token Index: 824

Text #19

Max Range: 1.2647. Min Range: -1.2647

Max Act: 1.0308. Min Act: -0.0000

Data Index: 773077 (C4 (Web Text))

Max Activating Token Index: 336