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

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

Neuron 1985 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4406. Min Range: -0.4406

Max Act: 0.4190. Min Act: -0.0001

Data Index: 310882 (C4 (Web Text))

Max Activating Token Index: 945

Text #1

Max Range: 0.4406. Min Range: -0.4406

Max Act: 0.4238. Min Act: -0.0001

Data Index: 698661 (C4 (Web Text))

Max Activating Token Index: 69

Text #2

Max Range: 0.4406. Min Range: -0.4406

Max Act: 0.3865. Min Act: -0.0001

Data Index: 1321058 (C4 (Web Text))

Max Activating Token Index: 51

Text #3

Max Range: 0.4406. Min Range: -0.4406

Max Act: 0.4341. Min Act: -0.0001

Data Index: 1295993 (C4 (Web Text))

Max Activating Token Index: 962

Text #4

Max Range: 0.4406. Min Range: -0.4406

Max Act: 0.4406. Min Act: -0.0001

Data Index: 440478 (C4 (Web Text))

Max Activating Token Index: 998

Text #5

Max Range: 0.4406. Min Range: -0.4406

Max Act: 0.4102. Min Act: -0.0001

Data Index: 870281 (C4 (Web Text))

Max Activating Token Index: 871

Text #6

Max Range: 0.4406. Min Range: -0.4406

Max Act: 0.3916. Min Act: -0.0001

Data Index: 892918 (C4 (Web Text))

Max Activating Token Index: 362

Text #7

Max Range: 0.4406. Min Range: -0.4406

Max Act: 0.4130. Min Act: -0.0001

Data Index: 350030 (C4 (Web Text))

Max Activating Token Index: 700

Text #8

Max Range: 0.4406. Min Range: -0.4406

Max Act: 0.4163. Min Act: -0.0001

Data Index: 366629 (C4 (Web Text))

Max Activating Token Index: 1002

Text #9

Max Range: 0.4406. Min Range: -0.4406

Max Act: 0.4054. Min Act: -0.0001

Data Index: 796817 (C4 (Web Text))

Max Activating Token Index: 803

Text #10

Max Range: 0.4406. Min Range: -0.4406

Max Act: 0.4055. Min Act: -0.0001

Data Index: 355356 (C4 (Web Text))

Max Activating Token Index: 754

Text #11

Max Range: 0.4406. Min Range: -0.4406

Max Act: 0.3682. Min Act: -0.0001

Data Index: 1224555 (C4 (Web Text))

Max Activating Token Index: 448

Text #12

Max Range: 0.4406. Min Range: -0.4406

Max Act: 0.3963. Min Act: -0.0001

Data Index: 835062 (C4 (Web Text))

Max Activating Token Index: 762

Text #13

Max Range: 0.4406. Min Range: -0.4406

Max Act: 0.3884. Min Act: -0.0001

Data Index: 75144 (C4 (Web Text))

Max Activating Token Index: 4

Text #14

Max Range: 0.4406. Min Range: -0.4406

Max Act: 0.3965. Min Act: -0.0001

Data Index: 486172 (C4 (Web Text))

Max Activating Token Index: 647

Text #15

Max Range: 0.4406. Min Range: -0.4406

Max Act: 0.3845. Min Act: -0.0001

Data Index: 260922 (C4 (Web Text))

Max Activating Token Index: 91

Text #16

Max Range: 0.4406. Min Range: -0.4406

Max Act: 0.3956. Min Act: -0.0001

Data Index: 567194 (C4 (Web Text))

Max Activating Token Index: 302

Text #17

Max Range: 0.4406. Min Range: -0.4406

Max Act: 0.3839. Min Act: -0.0001

Data Index: 1089353 (C4 (Web Text))

Max Activating Token Index: 313

Text #18

Max Range: 0.4406. Min Range: -0.4406

Max Act: 0.3999. Min Act: -0.0001

Data Index: 1183301 (C4 (Web Text))

Max Activating Token Index: 608

Text #19

Max Range: 0.4406. Min Range: -0.4406

Max Act: 0.4120. Min Act: -0.0001

Data Index: 412446 (C4 (Web Text))

Max Activating Token Index: 724