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

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

Neuron 2230 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3519. Min Range: -0.3519

Max Act: 0.3519. Min Act: -0.0001

Data Index: 1119003 (C4 (Web Text))

Max Activating Token Index: 770

Text #1

Max Range: 0.3519. Min Range: -0.3519

Max Act: 0.3170. Min Act: -0.0001

Data Index: 1177980 (C4 (Web Text))

Max Activating Token Index: 717

Text #2

Max Range: 0.3519. Min Range: -0.3519

Max Act: 0.2352. Min Act: -0.0001

Data Index: 769866 (C4 (Web Text))

Max Activating Token Index: 51

Text #3

Max Range: 0.3519. Min Range: -0.3519

Max Act: 0.2350. Min Act: -0.0001

Data Index: 1325408 (C4 (Web Text))

Max Activating Token Index: 356

Text #4

Max Range: 0.3519. Min Range: -0.3519

Max Act: 0.2135. Min Act: -0.0001

Data Index: 1588133 (Python Code)

Max Activating Token Index: 173

Text #5

Max Range: 0.3519. Min Range: -0.3519

Max Act: 0.2272. Min Act: -0.0001

Data Index: 137430 (C4 (Web Text))

Max Activating Token Index: 317

Text #6

Max Range: 0.3519. Min Range: -0.3519

Max Act: 0.2052. Min Act: -0.0001

Data Index: 1298916 (C4 (Web Text))

Max Activating Token Index: 397

Text #7

Max Range: 0.3519. Min Range: -0.3519

Max Act: 0.2332. Min Act: -0.0001

Data Index: 598839 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 0.3519. Min Range: -0.3519

Max Act: 0.2112. Min Act: -0.0002

Data Index: 623967 (C4 (Web Text))

Max Activating Token Index: 22

Text #9

Max Range: 0.3519. Min Range: -0.3519

Max Act: 0.2091. Min Act: -0.0001

Data Index: 669030 (C4 (Web Text))

Max Activating Token Index: 761

Text #10

Max Range: 0.3519. Min Range: -0.3519

Max Act: 0.2386. Min Act: -0.0001

Data Index: 1346224 (C4 (Web Text))

Max Activating Token Index: 710

Text #11

Max Range: 0.3519. Min Range: -0.3519

Max Act: 0.2063. Min Act: -0.0001

Data Index: 857040 (C4 (Web Text))

Max Activating Token Index: 101

Text #12

Max Range: 0.3519. Min Range: -0.3519

Max Act: 0.1918. Min Act: -0.0001

Data Index: 1445462 (Python Code)

Max Activating Token Index: 106

Text #13

Max Range: 0.3519. Min Range: -0.3519

Max Act: 0.2099. Min Act: -0.0001

Data Index: 478952 (C4 (Web Text))

Max Activating Token Index: 383

Text #14

Max Range: 0.3519. Min Range: -0.3519

Max Act: 0.2036. Min Act: -0.0001

Data Index: 97233 (C4 (Web Text))

Max Activating Token Index: 87

Text #15

Max Range: 0.3519. Min Range: -0.3519

Max Act: 0.2002. Min Act: -0.0001

Data Index: 1423284 (Python Code)

Max Activating Token Index: 576

Text #16

Max Range: 0.3519. Min Range: -0.3519

Max Act: 0.1835. Min Act: -0.0001

Data Index: 1318255 (C4 (Web Text))

Max Activating Token Index: 186

Text #17

Max Range: 0.3519. Min Range: -0.3519

Max Act: 0.2136. Min Act: -0.0001

Data Index: 1010335 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 0.3519. Min Range: -0.3519

Max Act: 0.2052. Min Act: -0.0001

Data Index: 444057 (C4 (Web Text))

Max Activating Token Index: 368

Text #19

Max Range: 0.3519. Min Range: -0.3519

Max Act: 0.1904. Min Act: -0.0001

Data Index: 734003 (C4 (Web Text))

Max Activating Token Index: 548