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

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

Neuron 4956 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: 3.4074. Min Range: -3.4074

Max Act: 3.4074. Min Act: -0.0000

Data Index: 384187 (C4 (Web Text))

Max Activating Token Index: 155

Text #1

Max Range: 3.4074. Min Range: -3.4074

Max Act: 2.6388. Min Act: -0.0001

Data Index: 1008473 (C4 (Web Text))

Max Activating Token Index: 167

Text #2

Max Range: 3.4074. Min Range: -3.4074

Max Act: 2.5815. Min Act: -0.0001

Data Index: 363031 (C4 (Web Text))

Max Activating Token Index: 299

Text #3

Max Range: 3.4074. Min Range: -3.4074

Max Act: 3.0263. Min Act: -0.0001

Data Index: 1271080 (C4 (Web Text))

Max Activating Token Index: 195

Text #4

Max Range: 3.4074. Min Range: -3.4074

Max Act: 2.4896. Min Act: -0.0001

Data Index: 1017278 (C4 (Web Text))

Max Activating Token Index: 259

Text #5

Max Range: 3.4074. Min Range: -3.4074

Max Act: 2.5799. Min Act: -0.0001

Data Index: 824875 (C4 (Web Text))

Max Activating Token Index: 817

Text #6

Max Range: 3.4074. Min Range: -3.4074

Max Act: 2.7322. Min Act: -0.0001

Data Index: 1183075 (C4 (Web Text))

Max Activating Token Index: 690

Text #7

Max Range: 3.4074. Min Range: -3.4074

Max Act: 2.3113. Min Act: -0.0001

Data Index: 369194 (C4 (Web Text))

Max Activating Token Index: 956

Text #8

Max Range: 3.4074. Min Range: -3.4074

Max Act: 2.6622. Min Act: -0.0001

Data Index: 712589 (C4 (Web Text))

Max Activating Token Index: 733

Text #9

Max Range: 3.4074. Min Range: -3.4074

Max Act: 2.4028. Min Act: -0.0000

Data Index: 749754 (C4 (Web Text))

Max Activating Token Index: 272

Text #10

Max Range: 3.4074. Min Range: -3.4074

Max Act: 2.5030. Min Act: -0.0001

Data Index: 633335 (C4 (Web Text))

Max Activating Token Index: 835

Text #11

Max Range: 3.4074. Min Range: -3.4074

Max Act: 2.8638. Min Act: -0.0001

Data Index: 890425 (C4 (Web Text))

Max Activating Token Index: 281

Text #12

Max Range: 3.4074. Min Range: -3.4074

Max Act: 2.5827. Min Act: -0.0001

Data Index: 256956 (C4 (Web Text))

Max Activating Token Index: 677

Text #13

Max Range: 3.4074. Min Range: -3.4074

Max Act: 2.7017. Min Act: -0.0001

Data Index: 1187651 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 3.4074. Min Range: -3.4074

Max Act: 2.4478. Min Act: -0.0001

Data Index: 977498 (C4 (Web Text))

Max Activating Token Index: 922

Text #15

Max Range: 3.4074. Min Range: -3.4074

Max Act: 2.4315. Min Act: -0.0000

Data Index: 613339 (C4 (Web Text))

Max Activating Token Index: 38

Text #16

Max Range: 3.4074. Min Range: -3.4074

Max Act: 2.4503. Min Act: -0.0000

Data Index: 164900 (C4 (Web Text))

Max Activating Token Index: 744

Text #17

Max Range: 3.4074. Min Range: -3.4074

Max Act: 2.6853. Min Act: -0.0001

Data Index: 361057 (C4 (Web Text))

Max Activating Token Index: 124

Text #18

Max Range: 3.4074. Min Range: -3.4074

Max Act: 2.2948. Min Act: -0.0001

Data Index: 572858 (C4 (Web Text))

Max Activating Token Index: 199

Text #19

Max Range: 3.4074. Min Range: -3.4074

Max Act: 2.2932. Min Act: -0.0001

Data Index: 500944 (C4 (Web Text))

Max Activating Token Index: 180