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

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

Neuron 3587 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: 0.3673. Min Range: -0.3673

Max Act: 0.3673. Min Act: -0.0002

Data Index: 509621 (C4 (Web Text))

Max Activating Token Index: 99

Text #1

Max Range: 0.3673. Min Range: -0.3673

Max Act: 0.3646. Min Act: -0.0002

Data Index: 325753 (C4 (Web Text))

Max Activating Token Index: 464

Text #2

Max Range: 0.3673. Min Range: -0.3673

Max Act: 0.3472. Min Act: -0.0002

Data Index: 644084 (C4 (Web Text))

Max Activating Token Index: 673

Text #3

Max Range: 0.3673. Min Range: -0.3673

Max Act: 0.3486. Min Act: -0.0002

Data Index: 18012 (C4 (Web Text))

Max Activating Token Index: 488

Text #4

Max Range: 0.3673. Min Range: -0.3673

Max Act: 0.3389. Min Act: -0.0002

Data Index: 292059 (C4 (Web Text))

Max Activating Token Index: 552

Text #5

Max Range: 0.3673. Min Range: -0.3673

Max Act: 0.3277. Min Act: -0.0002

Data Index: 1357319 (C4 (Web Text))

Max Activating Token Index: 79

Text #6

Max Range: 0.3673. Min Range: -0.3673

Max Act: 0.3309. Min Act: -0.0002

Data Index: 784156 (C4 (Web Text))

Max Activating Token Index: 590

Text #7

Max Range: 0.3673. Min Range: -0.3673

Max Act: 0.3173. Min Act: -0.0002

Data Index: 1039839 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 0.3673. Min Range: -0.3673

Max Act: 0.3065. Min Act: -0.0002

Data Index: 926805 (C4 (Web Text))

Max Activating Token Index: 452

Text #9

Max Range: 0.3673. Min Range: -0.3673

Max Act: 0.3037. Min Act: -0.0002

Data Index: 406160 (C4 (Web Text))

Max Activating Token Index: 370

Text #10

Max Range: 0.3673. Min Range: -0.3673

Max Act: 0.3115. Min Act: -0.0002

Data Index: 247196 (C4 (Web Text))

Max Activating Token Index: 190

Text #11

Max Range: 0.3673. Min Range: -0.3673

Max Act: 0.3022. Min Act: -0.0002

Data Index: 1057630 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 0.3673. Min Range: -0.3673

Max Act: 0.2991. Min Act: -0.0002

Data Index: 1036359 (C4 (Web Text))

Max Activating Token Index: 11

Text #13

Max Range: 0.3673. Min Range: -0.3673

Max Act: 0.2994. Min Act: -0.0002

Data Index: 50421 (C4 (Web Text))

Max Activating Token Index: 192

Text #14

Max Range: 0.3673. Min Range: -0.3673

Max Act: 0.3057. Min Act: -0.0002

Data Index: 418221 (C4 (Web Text))

Max Activating Token Index: 819

Text #15

Max Range: 0.3673. Min Range: -0.3673

Max Act: 0.3046. Min Act: -0.0002

Data Index: 1349805 (C4 (Web Text))

Max Activating Token Index: 108

Text #16

Max Range: 0.3673. Min Range: -0.3673

Max Act: 0.2896. Min Act: -0.0002

Data Index: 575867 (C4 (Web Text))

Max Activating Token Index: 231

Text #17

Max Range: 0.3673. Min Range: -0.3673

Max Act: 0.2925. Min Act: -0.0002

Data Index: 261526 (C4 (Web Text))

Max Activating Token Index: 343

Text #18

Max Range: 0.3673. Min Range: -0.3673

Max Act: 0.2917. Min Act: -0.0002

Data Index: 1283485 (C4 (Web Text))

Max Activating Token Index: 275

Text #19

Max Range: 0.3673. Min Range: -0.3673

Max Act: 0.2900. Min Act: -0.0002

Data Index: 793072 (C4 (Web Text))

Max Activating Token Index: 395