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

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

Neuron 2520 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7567. Min Range: -5.7567

Max Act: 5.2278. Min Act: -0.0001

Data Index: 734883 (C4 (Web Text))

Max Activating Token Index: 416

Text #1

Max Range: 5.7567. Min Range: -5.7567

Max Act: 5.7567. Min Act: -0.0001

Data Index: 1350076 (C4 (Web Text))

Max Activating Token Index: 296

Text #2

Max Range: 5.7567. Min Range: -5.7567

Max Act: 5.3452. Min Act: -0.0001

Data Index: 494169 (C4 (Web Text))

Max Activating Token Index: 106

Text #3

Max Range: 5.7567. Min Range: -5.7567

Max Act: 4.6049. Min Act: -0.0001

Data Index: 173506 (C4 (Web Text))

Max Activating Token Index: 707

Text #4

Max Range: 5.7567. Min Range: -5.7567

Max Act: 5.0933. Min Act: -0.0001

Data Index: 193742 (C4 (Web Text))

Max Activating Token Index: 159

Text #5

Max Range: 5.7567. Min Range: -5.7567

Max Act: 4.3933. Min Act: -0.0001

Data Index: 31885 (C4 (Web Text))

Max Activating Token Index: 129

Text #6

Max Range: 5.7567. Min Range: -5.7567

Max Act: 4.2042. Min Act: -0.0001

Data Index: 390829 (C4 (Web Text))

Max Activating Token Index: 280

Text #7

Max Range: 5.7567. Min Range: -5.7567

Max Act: 4.6258. Min Act: -0.0001

Data Index: 752573 (C4 (Web Text))

Max Activating Token Index: 532

Text #8

Max Range: 5.7567. Min Range: -5.7567

Max Act: 4.4736. Min Act: -0.0001

Data Index: 93642 (C4 (Web Text))

Max Activating Token Index: 383

Text #9

Max Range: 5.7567. Min Range: -5.7567

Max Act: 5.1171. Min Act: -0.0001

Data Index: 1174766 (C4 (Web Text))

Max Activating Token Index: 336

Text #10

Max Range: 5.7567. Min Range: -5.7567

Max Act: 4.4024. Min Act: -0.0001

Data Index: 517179 (C4 (Web Text))

Max Activating Token Index: 493

Text #11

Max Range: 5.7567. Min Range: -5.7567

Max Act: 4.3058. Min Act: -0.0001

Data Index: 937197 (C4 (Web Text))

Max Activating Token Index: 15

Text #12

Max Range: 5.7567. Min Range: -5.7567

Max Act: 4.1450. Min Act: -0.0001

Data Index: 335886 (C4 (Web Text))

Max Activating Token Index: 17

Text #13

Max Range: 5.7567. Min Range: -5.7567

Max Act: 4.2365. Min Act: -0.0001

Data Index: 187521 (C4 (Web Text))

Max Activating Token Index: 205

Text #14

Max Range: 5.7567. Min Range: -5.7567

Max Act: 4.0066. Min Act: -0.0001

Data Index: 422639 (C4 (Web Text))

Max Activating Token Index: 56

Text #15

Max Range: 5.7567. Min Range: -5.7567

Max Act: 4.6212. Min Act: -0.0001

Data Index: 177763 (C4 (Web Text))

Max Activating Token Index: 164

Text #16

Max Range: 5.7567. Min Range: -5.7567

Max Act: 4.2702. Min Act: -0.0001

Data Index: 761458 (C4 (Web Text))

Max Activating Token Index: 38

Text #17

Max Range: 5.7567. Min Range: -5.7567

Max Act: 4.0993. Min Act: -0.0001

Data Index: 13433 (C4 (Web Text))

Max Activating Token Index: 86

Text #18

Max Range: 5.7567. Min Range: -5.7567

Max Act: 4.2425. Min Act: -0.0001

Data Index: 954083 (C4 (Web Text))

Max Activating Token Index: 45

Text #19

Max Range: 5.7567. Min Range: -5.7567

Max Act: 4.0734. Min Act: -0.0001

Data Index: 1215469 (C4 (Web Text))

Max Activating Token Index: 493