Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1292 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2933. Min Act: -0.0000

Data Index: 818373 (C4 (Web Text))

Max Activating Token Index: 313

Text #1

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2784. Min Act: -0.0000

Data Index: 612819 (C4 (Web Text))

Max Activating Token Index: 583

Text #2

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.3067. Min Act: -0.0001

Data Index: 1121806 (C4 (Web Text))

Max Activating Token Index: 210

Text #3

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2216. Min Act: -0.0001

Data Index: 502470 (C4 (Web Text))

Max Activating Token Index: 770

Text #4

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2217. Min Act: -0.0000

Data Index: 992969 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2325. Min Act: -0.0000

Data Index: 935249 (C4 (Web Text))

Max Activating Token Index: 29

Text #6

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2310. Min Act: -0.0000

Data Index: 1184673 (C4 (Web Text))

Max Activating Token Index: 873

Text #7

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2385. Min Act: -0.0000

Data Index: 108381 (C4 (Web Text))

Max Activating Token Index: 100

Text #8

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2219. Min Act: -0.0000

Data Index: 683270 (C4 (Web Text))

Max Activating Token Index: 556

Text #9

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2180. Min Act: -0.0000

Data Index: 1259709 (C4 (Web Text))

Max Activating Token Index: 727

Text #10

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2045. Min Act: -0.0001

Data Index: 86470 (C4 (Web Text))

Max Activating Token Index: 581

Text #11

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.1974. Min Act: -0.0000

Data Index: 935568 (C4 (Web Text))

Max Activating Token Index: 272

Text #12

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2177. Min Act: -0.0000

Data Index: 1136681 (C4 (Web Text))

Max Activating Token Index: 94

Text #13

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2092. Min Act: -0.0001

Data Index: 1094359 (C4 (Web Text))

Max Activating Token Index: 170

Text #14

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2305. Min Act: -0.0001

Data Index: 832783 (C4 (Web Text))

Max Activating Token Index: 330

Text #15

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2081. Min Act: -0.0001

Data Index: 446736 (C4 (Web Text))

Max Activating Token Index: 88

Text #16

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.1943. Min Act: -0.0000

Data Index: 1295850 (C4 (Web Text))

Max Activating Token Index: 573

Text #17

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.1980. Min Act: -0.0000

Data Index: 901996 (C4 (Web Text))

Max Activating Token Index: 488

Text #18

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.1893. Min Act: -0.0001

Data Index: 352037 (C4 (Web Text))

Max Activating Token Index: 229

Text #19

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.1615. Min Act: -0.0000

Data Index: 24821 (C4 (Web Text))

Max Activating Token Index: 733