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

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

Neuron 169 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: 0.4944. Min Range: -0.4944

Max Act: 0.4944. Min Act: -0.0000

Data Index: 811673 (C4 (Web Text))

Max Activating Token Index: 486

Text #1

Max Range: 0.4944. Min Range: -0.4944

Max Act: 0.4711. Min Act: -0.0001

Data Index: 1276137 (C4 (Web Text))

Max Activating Token Index: 964

Text #2

Max Range: 0.4944. Min Range: -0.4944

Max Act: 0.4725. Min Act: -0.0001

Data Index: 194798 (C4 (Web Text))

Max Activating Token Index: 15

Text #3

Max Range: 0.4944. Min Range: -0.4944

Max Act: 0.4458. Min Act: -0.0001

Data Index: 911678 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 0.4944. Min Range: -0.4944

Max Act: 0.4255. Min Act: -0.0001

Data Index: 482125 (C4 (Web Text))

Max Activating Token Index: 967

Text #5

Max Range: 0.4944. Min Range: -0.4944

Max Act: 0.4292. Min Act: -0.0001

Data Index: 1001989 (C4 (Web Text))

Max Activating Token Index: 965

Text #6

Max Range: 0.4944. Min Range: -0.4944

Max Act: 0.4350. Min Act: -0.0000

Data Index: 531835 (C4 (Web Text))

Max Activating Token Index: 286

Text #7

Max Range: 0.4944. Min Range: -0.4944

Max Act: 0.4441. Min Act: -0.0001

Data Index: 81164 (C4 (Web Text))

Max Activating Token Index: 810

Text #8

Max Range: 0.4944. Min Range: -0.4944

Max Act: 0.4403. Min Act: -0.0001

Data Index: 1299747 (C4 (Web Text))

Max Activating Token Index: 90

Text #9

Max Range: 0.4944. Min Range: -0.4944

Max Act: 0.3902. Min Act: -0.0000

Data Index: 638327 (C4 (Web Text))

Max Activating Token Index: 816

Text #10

Max Range: 0.4944. Min Range: -0.4944

Max Act: 0.3879. Min Act: -0.0001

Data Index: 510909 (C4 (Web Text))

Max Activating Token Index: 727

Text #11

Max Range: 0.4944. Min Range: -0.4944

Max Act: 0.4095. Min Act: -0.0001

Data Index: 1098314 (C4 (Web Text))

Max Activating Token Index: 870

Text #12

Max Range: 0.4944. Min Range: -0.4944

Max Act: 0.4290. Min Act: -0.0001

Data Index: 162691 (C4 (Web Text))

Max Activating Token Index: 444

Text #13

Max Range: 0.4944. Min Range: -0.4944

Max Act: 0.3816. Min Act: -0.0000

Data Index: 586812 (C4 (Web Text))

Max Activating Token Index: 751

Text #14

Max Range: 0.4944. Min Range: -0.4944

Max Act: 0.4090. Min Act: -0.0001

Data Index: 1312759 (C4 (Web Text))

Max Activating Token Index: 432

Text #15

Max Range: 0.4944. Min Range: -0.4944

Max Act: 0.4060. Min Act: -0.0001

Data Index: 923313 (C4 (Web Text))

Max Activating Token Index: 135

Text #16

Max Range: 0.4944. Min Range: -0.4944

Max Act: 0.4052. Min Act: -0.0001

Data Index: 981604 (C4 (Web Text))

Max Activating Token Index: 937

Text #17

Max Range: 0.4944. Min Range: -0.4944

Max Act: 0.3903. Min Act: -0.0001

Data Index: 1299949 (C4 (Web Text))

Max Activating Token Index: 993

Text #18

Max Range: 0.4944. Min Range: -0.4944

Max Act: 0.4163. Min Act: -0.0001

Data Index: 1217097 (C4 (Web Text))

Max Activating Token Index: 94

Text #19

Max Range: 0.4944. Min Range: -0.4944

Max Act: 0.3943. Min Act: -0.0001

Data Index: 101802 (C4 (Web Text))

Max Activating Token Index: 396