Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1306 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.2609. Min Act: -0.0001

Data Index: 1106935 (C4 (Web Text))

Max Activating Token Index: 450

Text #1

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.2451. Min Act: -0.0001

Data Index: 905250 (C4 (Web Text))

Max Activating Token Index: 956

Text #2

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.2453. Min Act: -0.0001

Data Index: 743940 (C4 (Web Text))

Max Activating Token Index: 65

Text #3

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.2512. Min Act: -0.0001

Data Index: 1229348 (C4 (Web Text))

Max Activating Token Index: 487

Text #4

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.2552. Min Act: -0.0001

Data Index: 1013735 (C4 (Web Text))

Max Activating Token Index: 608

Text #5

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.2458. Min Act: -0.0001

Data Index: 849439 (C4 (Web Text))

Max Activating Token Index: 496

Text #6

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.2380. Min Act: -0.0000

Data Index: 1253628 (C4 (Web Text))

Max Activating Token Index: 582

Text #7

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.2525. Min Act: -0.0001

Data Index: 248921 (C4 (Web Text))

Max Activating Token Index: 108

Text #8

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.2186. Min Act: -0.0001

Data Index: 1057018 (C4 (Web Text))

Max Activating Token Index: 276

Text #9

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.2195. Min Act: -0.0000

Data Index: 747077 (C4 (Web Text))

Max Activating Token Index: 593

Text #10

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.2207. Min Act: -0.0001

Data Index: 869104 (C4 (Web Text))

Max Activating Token Index: 855

Text #11

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.2093. Min Act: -0.0000

Data Index: 826378 (C4 (Web Text))

Max Activating Token Index: 593

Text #12

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.2182. Min Act: -0.0001

Data Index: 83939 (C4 (Web Text))

Max Activating Token Index: 82

Text #13

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.2181. Min Act: -0.0001

Data Index: 244413 (C4 (Web Text))

Max Activating Token Index: 552

Text #14

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.1928. Min Act: -0.0001

Data Index: 1151370 (C4 (Web Text))

Max Activating Token Index: 645

Text #15

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.2094. Min Act: -0.0001

Data Index: 1048250 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.2174. Min Act: -0.0001

Data Index: 504067 (C4 (Web Text))

Max Activating Token Index: 977

Text #17

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.2133. Min Act: -0.0001

Data Index: 894470 (C4 (Web Text))

Max Activating Token Index: 736

Text #18

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.1969. Min Act: -0.0001

Data Index: 1318385 (C4 (Web Text))

Max Activating Token Index: 540

Text #19

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.2087. Min Act: -0.0001

Data Index: 752257 (C4 (Web Text))

Max Activating Token Index: 132