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

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

Neuron 1057 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2139. Min Range: -1.2139

Max Act: 1.2139. Min Act: -0.0000

Data Index: 837987 (C4 (Web Text))

Max Activating Token Index: 708

Text #1

Max Range: 1.2139. Min Range: -1.2139

Max Act: 1.1167. Min Act: -0.0000

Data Index: 384091 (C4 (Web Text))

Max Activating Token Index: 129

Text #2

Max Range: 1.2139. Min Range: -1.2139

Max Act: 1.0199. Min Act: -0.0000

Data Index: 1095021 (C4 (Web Text))

Max Activating Token Index: 79

Text #3

Max Range: 1.2139. Min Range: -1.2139

Max Act: 1.0382. Min Act: -0.0000

Data Index: 1306573 (C4 (Web Text))

Max Activating Token Index: 41

Text #4

Max Range: 1.2139. Min Range: -1.2139

Max Act: 1.0034. Min Act: -0.0000

Data Index: 725355 (C4 (Web Text))

Max Activating Token Index: 980

Text #5

Max Range: 1.2139. Min Range: -1.2139

Max Act: 0.7788. Min Act: -0.0000

Data Index: 335464 (C4 (Web Text))

Max Activating Token Index: 979

Text #6

Max Range: 1.2139. Min Range: -1.2139

Max Act: 0.7937. Min Act: -0.0000

Data Index: 1081397 (C4 (Web Text))

Max Activating Token Index: 340

Text #7

Max Range: 1.2139. Min Range: -1.2139

Max Act: 0.9515. Min Act: -0.0000

Data Index: 614101 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 1.2139. Min Range: -1.2139

Max Act: 0.9397. Min Act: -0.0000

Data Index: 416437 (C4 (Web Text))

Max Activating Token Index: 104

Text #9

Max Range: 1.2139. Min Range: -1.2139

Max Act: 0.9873. Min Act: -0.0000

Data Index: 184438 (C4 (Web Text))

Max Activating Token Index: 690

Text #10

Max Range: 1.2139. Min Range: -1.2139

Max Act: 0.9389. Min Act: -0.0000

Data Index: 438611 (C4 (Web Text))

Max Activating Token Index: 436

Text #11

Max Range: 1.2139. Min Range: -1.2139

Max Act: 0.8976. Min Act: -0.0000

Data Index: 374674 (C4 (Web Text))

Max Activating Token Index: 942

Text #12

Max Range: 1.2139. Min Range: -1.2139

Max Act: 0.8737. Min Act: -0.0000

Data Index: 991556 (C4 (Web Text))

Max Activating Token Index: 921

Text #13

Max Range: 1.2139. Min Range: -1.2139

Max Act: 0.8892. Min Act: -0.0000

Data Index: 992760 (C4 (Web Text))

Max Activating Token Index: 448

Text #14

Max Range: 1.2139. Min Range: -1.2139

Max Act: 0.9111. Min Act: -0.0000

Data Index: 259816 (C4 (Web Text))

Max Activating Token Index: 725

Text #15

Max Range: 1.2139. Min Range: -1.2139

Max Act: 0.8983. Min Act: -0.0000

Data Index: 437047 (C4 (Web Text))

Max Activating Token Index: 421

Text #16

Max Range: 1.2139. Min Range: -1.2139

Max Act: 0.8161. Min Act: -0.0000

Data Index: 399949 (C4 (Web Text))

Max Activating Token Index: 973

Text #17

Max Range: 1.2139. Min Range: -1.2139

Max Act: 0.8700. Min Act: -0.0000

Data Index: 356000 (C4 (Web Text))

Max Activating Token Index: 630

Text #18

Max Range: 1.2139. Min Range: -1.2139

Max Act: 0.7920. Min Act: -0.0000

Data Index: 260102 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 1.2139. Min Range: -1.2139

Max Act: 0.8605. Min Act: -0.0000

Data Index: 1122714 (C4 (Web Text))

Max Activating Token Index: 555