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

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

Neuron 2936 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: 4.1983. Min Range: -4.1983

Max Act: 4.1983. Min Act: -0.0000

Data Index: 1235362 (C4 (Web Text))

Max Activating Token Index: 1015

Text #1

Max Range: 4.1983. Min Range: -4.1983

Max Act: 3.7422. Min Act: -0.0000

Data Index: 43335 (C4 (Web Text))

Max Activating Token Index: 254

Text #2

Max Range: 4.1983. Min Range: -4.1983

Max Act: 3.5400. Min Act: -0.0000

Data Index: 748033 (C4 (Web Text))

Max Activating Token Index: 474

Text #3

Max Range: 4.1983. Min Range: -4.1983

Max Act: 3.3134. Min Act: -0.0000

Data Index: 247488 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 4.1983. Min Range: -4.1983

Max Act: 3.5365. Min Act: -0.0000

Data Index: 308747 (C4 (Web Text))

Max Activating Token Index: 685

Text #5

Max Range: 4.1983. Min Range: -4.1983

Max Act: 3.1995. Min Act: -0.0000

Data Index: 1598827 (Python Code)

Max Activating Token Index: 501

Text #6

Max Range: 4.1983. Min Range: -4.1983

Max Act: 3.3356. Min Act: -0.0000

Data Index: 1252779 (C4 (Web Text))

Max Activating Token Index: 663

Text #7

Max Range: 4.1983. Min Range: -4.1983

Max Act: 3.3287. Min Act: -0.0000

Data Index: 1353895 (C4 (Web Text))

Max Activating Token Index: 788

Text #8

Max Range: 4.1983. Min Range: -4.1983

Max Act: 3.1036. Min Act: -0.0000

Data Index: 839349 (C4 (Web Text))

Max Activating Token Index: 842

Text #9

Max Range: 4.1983. Min Range: -4.1983

Max Act: 3.2656. Min Act: -0.0000

Data Index: 1507409 (Python Code)

Max Activating Token Index: 977

Text #10

Max Range: 4.1983. Min Range: -4.1983

Max Act: 3.2296. Min Act: -0.0000

Data Index: 1107477 (C4 (Web Text))

Max Activating Token Index: 394

Text #11

Max Range: 4.1983. Min Range: -4.1983

Max Act: 3.1941. Min Act: -0.0000

Data Index: 202071 (C4 (Web Text))

Max Activating Token Index: 1006

Text #12

Max Range: 4.1983. Min Range: -4.1983

Max Act: 3.2067. Min Act: -0.0000

Data Index: 1010275 (C4 (Web Text))

Max Activating Token Index: 5

Text #13

Max Range: 4.1983. Min Range: -4.1983

Max Act: 3.0537. Min Act: -0.0000

Data Index: 1471228 (Python Code)

Max Activating Token Index: 833

Text #14

Max Range: 4.1983. Min Range: -4.1983

Max Act: 3.0217. Min Act: -0.0000

Data Index: 618816 (C4 (Web Text))

Max Activating Token Index: 683

Text #15

Max Range: 4.1983. Min Range: -4.1983

Max Act: 3.0027. Min Act: -0.0000

Data Index: 1327630 (C4 (Web Text))

Max Activating Token Index: 9

Text #16

Max Range: 4.1983. Min Range: -4.1983

Max Act: 3.1359. Min Act: -0.0000

Data Index: 1452707 (Python Code)

Max Activating Token Index: 897

Text #17

Max Range: 4.1983. Min Range: -4.1983

Max Act: 3.1344. Min Act: -0.0000

Data Index: 892819 (C4 (Web Text))

Max Activating Token Index: 229

Text #18

Max Range: 4.1983. Min Range: -4.1983

Max Act: 2.9694. Min Act: -0.0000

Data Index: 485392 (C4 (Web Text))

Max Activating Token Index: 899

Text #19

Max Range: 4.1983. Min Range: -4.1983

Max Act: 3.2583. Min Act: -0.0000

Data Index: 105031 (C4 (Web Text))

Max Activating Token Index: 83