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

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

Neuron 3593 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.1154. Min Act: -0.0002

Data Index: 1191648 (C4 (Web Text))

Max Activating Token Index: 268

Text #1

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0936. Min Act: -0.0002

Data Index: 967241 (C4 (Web Text))

Max Activating Token Index: 958

Text #2

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0907. Min Act: -0.0002

Data Index: 948517 (C4 (Web Text))

Max Activating Token Index: 402

Text #3

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0875. Min Act: -0.0002

Data Index: 760716 (C4 (Web Text))

Max Activating Token Index: 368

Text #4

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0896. Min Act: -0.0002

Data Index: 553924 (C4 (Web Text))

Max Activating Token Index: 492

Text #5

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0884. Min Act: -0.0002

Data Index: 1482795 (Python Code)

Max Activating Token Index: 439

Text #6

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0889. Min Act: -0.0002

Data Index: 976106 (C4 (Web Text))

Max Activating Token Index: 816

Text #7

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0880. Min Act: -0.0002

Data Index: 580980 (C4 (Web Text))

Max Activating Token Index: 27

Text #8

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0842. Min Act: -0.0002

Data Index: 540758 (C4 (Web Text))

Max Activating Token Index: 209

Text #9

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0846. Min Act: -0.0002

Data Index: 1068314 (C4 (Web Text))

Max Activating Token Index: 543

Text #10

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0842. Min Act: -0.0002

Data Index: 1494421 (Python Code)

Max Activating Token Index: 223

Text #11

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0817. Min Act: -0.0002

Data Index: 1456716 (Python Code)

Max Activating Token Index: 7

Text #12

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0810. Min Act: -0.0002

Data Index: 1444818 (Python Code)

Max Activating Token Index: 453

Text #13

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0814. Min Act: -0.0002

Data Index: 306555 (C4 (Web Text))

Max Activating Token Index: 341

Text #14

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0804. Min Act: -0.0002

Data Index: 1382763 (Python Code)

Max Activating Token Index: 777

Text #15

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0819. Min Act: -0.0002

Data Index: 1258548 (C4 (Web Text))

Max Activating Token Index: 93

Text #16

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0801. Min Act: -0.0002

Data Index: 718970 (C4 (Web Text))

Max Activating Token Index: 287

Text #17

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0800. Min Act: -0.0002

Data Index: 1047138 (C4 (Web Text))

Max Activating Token Index: 960

Text #18

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0784. Min Act: -0.0002

Data Index: 596371 (C4 (Web Text))

Max Activating Token Index: 632

Text #19

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0778. Min Act: -0.0002

Data Index: 89984 (C4 (Web Text))

Max Activating Token Index: 630