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

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

Neuron 905 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5647. Min Range: -2.5647

Max Act: 2.5647. Min Act: -0.0000

Data Index: 707955 (C4 (Web Text))

Max Activating Token Index: 470

Text #1

Max Range: 2.5647. Min Range: -2.5647

Max Act: 2.1489. Min Act: -0.0000

Data Index: 51100 (C4 (Web Text))

Max Activating Token Index: 921

Text #2

Max Range: 2.5647. Min Range: -2.5647

Max Act: 1.9870. Min Act: -0.0000

Data Index: 532910 (C4 (Web Text))

Max Activating Token Index: 987

Text #3

Max Range: 2.5647. Min Range: -2.5647

Max Act: 2.1470. Min Act: -0.0000

Data Index: 605514 (C4 (Web Text))

Max Activating Token Index: 803

Text #4

Max Range: 2.5647. Min Range: -2.5647

Max Act: 1.8080. Min Act: -0.0000

Data Index: 400052 (C4 (Web Text))

Max Activating Token Index: 898

Text #5

Max Range: 2.5647. Min Range: -2.5647

Max Act: 1.8995. Min Act: -0.0000

Data Index: 717984 (C4 (Web Text))

Max Activating Token Index: 987

Text #6

Max Range: 2.5647. Min Range: -2.5647

Max Act: 1.8306. Min Act: -0.0000

Data Index: 459558 (C4 (Web Text))

Max Activating Token Index: 1011

Text #7

Max Range: 2.5647. Min Range: -2.5647

Max Act: 1.7423. Min Act: -0.0000

Data Index: 553431 (C4 (Web Text))

Max Activating Token Index: 871

Text #8

Max Range: 2.5647. Min Range: -2.5647

Max Act: 2.0007. Min Act: -0.0000

Data Index: 664835 (C4 (Web Text))

Max Activating Token Index: 859

Text #9

Max Range: 2.5647. Min Range: -2.5647

Max Act: 1.7194. Min Act: -0.0000

Data Index: 598395 (C4 (Web Text))

Max Activating Token Index: 989

Text #10

Max Range: 2.5647. Min Range: -2.5647

Max Act: 1.7106. Min Act: -0.0000

Data Index: 179949 (C4 (Web Text))

Max Activating Token Index: 445

Text #11

Max Range: 2.5647. Min Range: -2.5647

Max Act: 1.6630. Min Act: -0.0000

Data Index: 994911 (C4 (Web Text))

Max Activating Token Index: 153

Text #12

Max Range: 2.5647. Min Range: -2.5647

Max Act: 1.6718. Min Act: -0.0000

Data Index: 1190212 (C4 (Web Text))

Max Activating Token Index: 421

Text #13

Max Range: 2.5647. Min Range: -2.5647

Max Act: 1.6179. Min Act: -0.0000

Data Index: 1453241 (Python Code)

Max Activating Token Index: 503

Text #14

Max Range: 2.5647. Min Range: -2.5647

Max Act: 1.2180. Min Act: -0.0000

Data Index: 1258455 (C4 (Web Text))

Max Activating Token Index: 672

Text #15

Max Range: 2.5647. Min Range: -2.5647

Max Act: 1.5088. Min Act: -0.0000

Data Index: 803956 (C4 (Web Text))

Max Activating Token Index: 325

Text #16

Max Range: 2.5647. Min Range: -2.5647

Max Act: 1.5656. Min Act: -0.0000

Data Index: 135988 (C4 (Web Text))

Max Activating Token Index: 465

Text #17

Max Range: 2.5647. Min Range: -2.5647

Max Act: 1.7147. Min Act: -0.0000

Data Index: 395353 (C4 (Web Text))

Max Activating Token Index: 213

Text #18

Max Range: 2.5647. Min Range: -2.5647

Max Act: 1.4944. Min Act: -0.0000

Data Index: 81606 (C4 (Web Text))

Max Activating Token Index: 414

Text #19

Max Range: 2.5647. Min Range: -2.5647

Max Act: 1.4681. Min Act: -0.0000

Data Index: 1015637 (C4 (Web Text))

Max Activating Token Index: 802