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

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

Neuron 13 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1456. Min Range: -1.1456

Max Act: 1.1456. Min Act: -0.0000

Data Index: 908665 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 1.1456. Min Range: -1.1456

Max Act: 0.8392. Min Act: 0.0000

Data Index: 1078031 (C4 (Web Text))

Max Activating Token Index: 337

Text #2

Max Range: 1.1456. Min Range: -1.1456

Max Act: 0.8171. Min Act: -0.0000

Data Index: 70090 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 1.1456. Min Range: -1.1456

Max Act: 0.7612. Min Act: -0.0000

Data Index: 537579 (C4 (Web Text))

Max Activating Token Index: 125

Text #4

Max Range: 1.1456. Min Range: -1.1456

Max Act: 0.7461. Min Act: -0.0000

Data Index: 1066623 (C4 (Web Text))

Max Activating Token Index: 954

Text #5

Max Range: 1.1456. Min Range: -1.1456

Max Act: 0.7153. Min Act: -0.0000

Data Index: 672844 (C4 (Web Text))

Max Activating Token Index: 951

Text #6

Max Range: 1.1456. Min Range: -1.1456

Max Act: 0.7042. Min Act: -0.0000

Data Index: 187051 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 1.1456. Min Range: -1.1456

Max Act: 0.7319. Min Act: -0.0000

Data Index: 468562 (C4 (Web Text))

Max Activating Token Index: 765

Text #8

Max Range: 1.1456. Min Range: -1.1456

Max Act: 0.6841. Min Act: -0.0000

Data Index: 282143 (C4 (Web Text))

Max Activating Token Index: 168

Text #9

Max Range: 1.1456. Min Range: -1.1456

Max Act: 0.6847. Min Act: -0.0000

Data Index: 967028 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 1.1456. Min Range: -1.1456

Max Act: 0.6793. Min Act: -0.0000

Data Index: 210879 (C4 (Web Text))

Max Activating Token Index: 559

Text #11

Max Range: 1.1456. Min Range: -1.1456

Max Act: 0.6461. Min Act: -0.0000

Data Index: 216914 (C4 (Web Text))

Max Activating Token Index: 547

Text #12

Max Range: 1.1456. Min Range: -1.1456

Max Act: 0.6523. Min Act: -0.0000

Data Index: 1336146 (C4 (Web Text))

Max Activating Token Index: 79

Text #13

Max Range: 1.1456. Min Range: -1.1456

Max Act: 0.6070. Min Act: -0.0000

Data Index: 361749 (C4 (Web Text))

Max Activating Token Index: 227

Text #14

Max Range: 1.1456. Min Range: -1.1456

Max Act: 0.6242. Min Act: -0.0000

Data Index: 516312 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 1.1456. Min Range: -1.1456

Max Act: 0.6394. Min Act: -0.0000

Data Index: 960265 (C4 (Web Text))

Max Activating Token Index: 227

Text #16

Max Range: 1.1456. Min Range: -1.1456

Max Act: 0.6348. Min Act: -0.0000

Data Index: 537603 (C4 (Web Text))

Max Activating Token Index: 217

Text #17

Max Range: 1.1456. Min Range: -1.1456

Max Act: 0.6333. Min Act: -0.0000

Data Index: 245912 (C4 (Web Text))

Max Activating Token Index: 101

Text #18

Max Range: 1.1456. Min Range: -1.1456

Max Act: 0.6197. Min Act: -0.0000

Data Index: 452979 (C4 (Web Text))

Max Activating Token Index: 807

Text #19

Max Range: 1.1456. Min Range: -1.1456

Max Act: 0.6580. Min Act: -0.0000

Data Index: 578946 (C4 (Web Text))

Max Activating Token Index: 301