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

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

Neuron 2098 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: 0.9006. Min Range: -0.9006

Max Act: 0.9006. Min Act: -0.0000

Data Index: 982228 (C4 (Web Text))

Max Activating Token Index: 127

Text #1

Max Range: 0.9006. Min Range: -0.9006

Max Act: 0.8297. Min Act: -0.0000

Data Index: 69288 (C4 (Web Text))

Max Activating Token Index: 427

Text #2

Max Range: 0.9006. Min Range: -0.9006

Max Act: 0.8419. Min Act: -0.0000

Data Index: 922097 (C4 (Web Text))

Max Activating Token Index: 674

Text #3

Max Range: 0.9006. Min Range: -0.9006

Max Act: 0.7072. Min Act: -0.0000

Data Index: 1050155 (C4 (Web Text))

Max Activating Token Index: 813

Text #4

Max Range: 0.9006. Min Range: -0.9006

Max Act: 0.8008. Min Act: -0.0000

Data Index: 954087 (C4 (Web Text))

Max Activating Token Index: 157

Text #5

Max Range: 0.9006. Min Range: -0.9006

Max Act: 0.8123. Min Act: -0.0000

Data Index: 669561 (C4 (Web Text))

Max Activating Token Index: 316

Text #6

Max Range: 0.9006. Min Range: -0.9006

Max Act: 0.7788. Min Act: -0.0000

Data Index: 541887 (C4 (Web Text))

Max Activating Token Index: 716

Text #7

Max Range: 0.9006. Min Range: -0.9006

Max Act: 0.8177. Min Act: -0.0000

Data Index: 1005676 (C4 (Web Text))

Max Activating Token Index: 897

Text #8

Max Range: 0.9006. Min Range: -0.9006

Max Act: 0.8080. Min Act: -0.0000

Data Index: 371519 (C4 (Web Text))

Max Activating Token Index: 734

Text #9

Max Range: 0.9006. Min Range: -0.9006

Max Act: 0.8105. Min Act: -0.0000

Data Index: 835982 (C4 (Web Text))

Max Activating Token Index: 615

Text #10

Max Range: 0.9006. Min Range: -0.9006

Max Act: 0.7276. Min Act: -0.0000

Data Index: 361071 (C4 (Web Text))

Max Activating Token Index: 416

Text #11

Max Range: 0.9006. Min Range: -0.9006

Max Act: 0.7336. Min Act: -0.0000

Data Index: 922683 (C4 (Web Text))

Max Activating Token Index: 647

Text #12

Max Range: 0.9006. Min Range: -0.9006

Max Act: 0.7472. Min Act: -0.0000

Data Index: 183390 (C4 (Web Text))

Max Activating Token Index: 591

Text #13

Max Range: 0.9006. Min Range: -0.9006

Max Act: 0.7161. Min Act: -0.0000

Data Index: 109639 (C4 (Web Text))

Max Activating Token Index: 131

Text #14

Max Range: 0.9006. Min Range: -0.9006

Max Act: 0.7517. Min Act: -0.0000

Data Index: 211556 (C4 (Web Text))

Max Activating Token Index: 550

Text #15

Max Range: 0.9006. Min Range: -0.9006

Max Act: 0.7737. Min Act: -0.0000

Data Index: 975095 (C4 (Web Text))

Max Activating Token Index: 229

Text #16

Max Range: 0.9006. Min Range: -0.9006

Max Act: 0.7463. Min Act: -0.0000

Data Index: 998365 (C4 (Web Text))

Max Activating Token Index: 1004

Text #17

Max Range: 0.9006. Min Range: -0.9006

Max Act: 0.7366. Min Act: -0.0000

Data Index: 373271 (C4 (Web Text))

Max Activating Token Index: 141

Text #18

Max Range: 0.9006. Min Range: -0.9006

Max Act: 0.6940. Min Act: -0.0000

Data Index: 788525 (C4 (Web Text))

Max Activating Token Index: 84

Text #19

Max Range: 0.9006. Min Range: -0.9006

Max Act: 0.6817. Min Act: -0.0000

Data Index: 616725 (C4 (Web Text))

Max Activating Token Index: 513