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

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

Neuron 4591 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: 0.2983. Min Range: -0.2983

Max Act: 0.2281. Min Act: -0.0000

Data Index: 296079 (C4 (Web Text))

Max Activating Token Index: 813

Text #1

Max Range: 0.2983. Min Range: -0.2983

Max Act: 0.2619. Min Act: -0.0000

Data Index: 175461 (C4 (Web Text))

Max Activating Token Index: 686

Text #2

Max Range: 0.2983. Min Range: -0.2983

Max Act: 0.2885. Min Act: -0.0000

Data Index: 1117135 (C4 (Web Text))

Max Activating Token Index: 935

Text #3

Max Range: 0.2983. Min Range: -0.2983

Max Act: 0.2700. Min Act: -0.0000

Data Index: 1212740 (C4 (Web Text))

Max Activating Token Index: 962

Text #4

Max Range: 0.2983. Min Range: -0.2983

Max Act: 0.2983. Min Act: -0.0000

Data Index: 975925 (C4 (Web Text))

Max Activating Token Index: 658

Text #5

Max Range: 0.2983. Min Range: -0.2983

Max Act: 0.1990. Min Act: -0.0000

Data Index: 1021225 (C4 (Web Text))

Max Activating Token Index: 133

Text #6

Max Range: 0.2983. Min Range: -0.2983

Max Act: 0.2098. Min Act: -0.0000

Data Index: 1223631 (C4 (Web Text))

Max Activating Token Index: 970

Text #7

Max Range: 0.2983. Min Range: -0.2983

Max Act: 0.2119. Min Act: -0.0000

Data Index: 915039 (C4 (Web Text))

Max Activating Token Index: 197

Text #8

Max Range: 0.2983. Min Range: -0.2983

Max Act: 0.2085. Min Act: -0.0000

Data Index: 552600 (C4 (Web Text))

Max Activating Token Index: 352

Text #9

Max Range: 0.2983. Min Range: -0.2983

Max Act: 0.1923. Min Act: -0.0000

Data Index: 581098 (C4 (Web Text))

Max Activating Token Index: 88

Text #10

Max Range: 0.2983. Min Range: -0.2983

Max Act: 0.1335. Min Act: -0.0000

Data Index: 937835 (C4 (Web Text))

Max Activating Token Index: 703

Text #11

Max Range: 0.2983. Min Range: -0.2983

Max Act: 0.1217. Min Act: -0.0000

Data Index: 412574 (C4 (Web Text))

Max Activating Token Index: 716

Text #12

Max Range: 0.2983. Min Range: -0.2983

Max Act: 0.1381. Min Act: -0.0000

Data Index: 66078 (C4 (Web Text))

Max Activating Token Index: 184

Text #13

Max Range: 0.2983. Min Range: -0.2983

Max Act: 0.1460. Min Act: -0.0000

Data Index: 690002 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 0.2983. Min Range: -0.2983

Max Act: 0.1103. Min Act: -0.0000

Data Index: 601219 (C4 (Web Text))

Max Activating Token Index: 533

Text #15

Max Range: 0.2983. Min Range: -0.2983

Max Act: 0.0978. Min Act: -0.0000

Data Index: 605800 (C4 (Web Text))

Max Activating Token Index: 60

Text #16

Max Range: 0.2983. Min Range: -0.2983

Max Act: 0.0974. Min Act: -0.0000

Data Index: 1094131 (C4 (Web Text))

Max Activating Token Index: 941

Text #17

Max Range: 0.2983. Min Range: -0.2983

Max Act: 0.0963. Min Act: -0.0000

Data Index: 1130611 (C4 (Web Text))

Max Activating Token Index: 479

Text #18

Max Range: 0.2983. Min Range: -0.2983

Max Act: 0.0961. Min Act: -0.0000

Data Index: 1172178 (C4 (Web Text))

Max Activating Token Index: 958

Text #19

Max Range: 0.2983. Min Range: -0.2983

Max Act: 0.1041. Min Act: -0.0000

Data Index: 747452 (C4 (Web Text))

Max Activating Token Index: 197