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

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

Neuron 3606 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4852. Min Range: -0.4852

Max Act: 0.4852. Min Act: -0.0000

Data Index: 532068 (C4 (Web Text))

Max Activating Token Index: 705

Text #1

Max Range: 0.4852. Min Range: -0.4852

Max Act: 0.4655. Min Act: -0.0000

Data Index: 310192 (C4 (Web Text))

Max Activating Token Index: 734

Text #2

Max Range: 0.4852. Min Range: -0.4852

Max Act: 0.4330. Min Act: -0.0001

Data Index: 236061 (C4 (Web Text))

Max Activating Token Index: 817

Text #3

Max Range: 0.4852. Min Range: -0.4852

Max Act: 0.4728. Min Act: -0.0000

Data Index: 1172952 (C4 (Web Text))

Max Activating Token Index: 781

Text #4

Max Range: 0.4852. Min Range: -0.4852

Max Act: 0.4287. Min Act: -0.0000

Data Index: 920970 (C4 (Web Text))

Max Activating Token Index: 57

Text #5

Max Range: 0.4852. Min Range: -0.4852

Max Act: 0.4208. Min Act: -0.0000

Data Index: 246283 (C4 (Web Text))

Max Activating Token Index: 454

Text #6

Max Range: 0.4852. Min Range: -0.4852

Max Act: 0.4182. Min Act: -0.0000

Data Index: 1129661 (C4 (Web Text))

Max Activating Token Index: 966

Text #7

Max Range: 0.4852. Min Range: -0.4852

Max Act: 0.4054. Min Act: -0.0001

Data Index: 363775 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 0.4852. Min Range: -0.4852

Max Act: 0.4152. Min Act: -0.0001

Data Index: 649207 (C4 (Web Text))

Max Activating Token Index: 876

Text #9

Max Range: 0.4852. Min Range: -0.4852

Max Act: 0.4113. Min Act: -0.0000

Data Index: 1144207 (C4 (Web Text))

Max Activating Token Index: 439

Text #10

Max Range: 0.4852. Min Range: -0.4852

Max Act: 0.4074. Min Act: -0.0000

Data Index: 1298417 (C4 (Web Text))

Max Activating Token Index: 934

Text #11

Max Range: 0.4852. Min Range: -0.4852

Max Act: 0.3781. Min Act: -0.0000

Data Index: 1055736 (C4 (Web Text))

Max Activating Token Index: 223

Text #12

Max Range: 0.4852. Min Range: -0.4852

Max Act: 0.4016. Min Act: -0.0000

Data Index: 956 (C4 (Web Text))

Max Activating Token Index: 82

Text #13

Max Range: 0.4852. Min Range: -0.4852

Max Act: 0.3673. Min Act: -0.0001

Data Index: 245397 (C4 (Web Text))

Max Activating Token Index: 639

Text #14

Max Range: 0.4852. Min Range: -0.4852

Max Act: 0.3689. Min Act: -0.0000

Data Index: 37068 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 0.4852. Min Range: -0.4852

Max Act: 0.3808. Min Act: -0.0001

Data Index: 895958 (C4 (Web Text))

Max Activating Token Index: 602

Text #16

Max Range: 0.4852. Min Range: -0.4852

Max Act: 0.3900. Min Act: -0.0000

Data Index: 582421 (C4 (Web Text))

Max Activating Token Index: 849

Text #17

Max Range: 0.4852. Min Range: -0.4852

Max Act: 0.3901. Min Act: -0.0000

Data Index: 1353669 (C4 (Web Text))

Max Activating Token Index: 792

Text #18

Max Range: 0.4852. Min Range: -0.4852

Max Act: 0.3728. Min Act: -0.0001

Data Index: 938121 (C4 (Web Text))

Max Activating Token Index: 77

Text #19

Max Range: 0.4852. Min Range: -0.4852

Max Act: 0.3769. Min Act: -0.0001

Data Index: 873835 (C4 (Web Text))

Max Activating Token Index: 754