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

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

Neuron 1929 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: 2.7121. Min Range: -2.7121

Max Act: 2.7121. Min Act: -0.0000

Data Index: 235788 (C4 (Web Text))

Max Activating Token Index: 748

Text #1

Max Range: 2.7121. Min Range: -2.7121

Max Act: 2.5997. Min Act: -0.0000

Data Index: 483958 (C4 (Web Text))

Max Activating Token Index: 670

Text #2

Max Range: 2.7121. Min Range: -2.7121

Max Act: 2.4333. Min Act: -0.0000

Data Index: 1102703 (C4 (Web Text))

Max Activating Token Index: 441

Text #3

Max Range: 2.7121. Min Range: -2.7121

Max Act: 2.5566. Min Act: -0.0000

Data Index: 743939 (C4 (Web Text))

Max Activating Token Index: 691

Text #4

Max Range: 2.7121. Min Range: -2.7121

Max Act: 2.4158. Min Act: -0.0000

Data Index: 775103 (C4 (Web Text))

Max Activating Token Index: 51

Text #5

Max Range: 2.7121. Min Range: -2.7121

Max Act: 2.2704. Min Act: -0.0000

Data Index: 615839 (C4 (Web Text))

Max Activating Token Index: 808

Text #6

Max Range: 2.7121. Min Range: -2.7121

Max Act: 2.3891. Min Act: -0.0000

Data Index: 487424 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 2.7121. Min Range: -2.7121

Max Act: 2.2326. Min Act: -0.0000

Data Index: 440987 (C4 (Web Text))

Max Activating Token Index: 960

Text #8

Max Range: 2.7121. Min Range: -2.7121

Max Act: 2.2250. Min Act: -0.0000

Data Index: 1157270 (C4 (Web Text))

Max Activating Token Index: 231

Text #9

Max Range: 2.7121. Min Range: -2.7121

Max Act: 2.3082. Min Act: -0.0000

Data Index: 1282990 (C4 (Web Text))

Max Activating Token Index: 384

Text #10

Max Range: 2.7121. Min Range: -2.7121

Max Act: 2.3706. Min Act: -0.0000

Data Index: 482531 (C4 (Web Text))

Max Activating Token Index: 982

Text #11

Max Range: 2.7121. Min Range: -2.7121

Max Act: 2.1387. Min Act: -0.0000

Data Index: 842733 (C4 (Web Text))

Max Activating Token Index: 698

Text #12

Max Range: 2.7121. Min Range: -2.7121

Max Act: 2.1211. Min Act: -0.0000

Data Index: 1571670 (Python Code)

Max Activating Token Index: 768

Text #13

Max Range: 2.7121. Min Range: -2.7121

Max Act: 2.2276. Min Act: -0.0000

Data Index: 69692 (C4 (Web Text))

Max Activating Token Index: 273

Text #14

Max Range: 2.7121. Min Range: -2.7121

Max Act: 2.2367. Min Act: -0.0000

Data Index: 115388 (C4 (Web Text))

Max Activating Token Index: 170

Text #15

Max Range: 2.7121. Min Range: -2.7121

Max Act: 2.2402. Min Act: -0.0000

Data Index: 820777 (C4 (Web Text))

Max Activating Token Index: 591

Text #16

Max Range: 2.7121. Min Range: -2.7121

Max Act: 2.2429. Min Act: -0.0000

Data Index: 294356 (C4 (Web Text))

Max Activating Token Index: 786

Text #17

Max Range: 2.7121. Min Range: -2.7121

Max Act: 2.3261. Min Act: -0.0000

Data Index: 431053 (C4 (Web Text))

Max Activating Token Index: 829

Text #18

Max Range: 2.7121. Min Range: -2.7121

Max Act: 2.1979. Min Act: -0.0000

Data Index: 1132529 (C4 (Web Text))

Max Activating Token Index: 30

Text #19

Max Range: 2.7121. Min Range: -2.7121

Max Act: 2.0870. Min Act: -0.0000

Data Index: 1041946 (C4 (Web Text))

Max Activating Token Index: 303