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

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

Neuron 2609 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: 0.4259. Min Range: -0.4259

Max Act: 0.4259. Min Act: -0.0003

Data Index: 300397 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.4216. Min Act: -0.0002

Data Index: 1323949 (C4 (Web Text))

Max Activating Token Index: 572

Text #2

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.4171. Min Act: -0.0002

Data Index: 668991 (C4 (Web Text))

Max Activating Token Index: 31

Text #3

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.4114. Min Act: -0.0002

Data Index: 484629 (C4 (Web Text))

Max Activating Token Index: 720

Text #4

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.4148. Min Act: -0.0002

Data Index: 170697 (C4 (Web Text))

Max Activating Token Index: 11

Text #5

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.4140. Min Act: -0.0003

Data Index: 483744 (C4 (Web Text))

Max Activating Token Index: 730

Text #6

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3986. Min Act: -0.0002

Data Index: 550198 (C4 (Web Text))

Max Activating Token Index: 602

Text #7

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3944. Min Act: -0.0002

Data Index: 472495 (C4 (Web Text))

Max Activating Token Index: 187

Text #8

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3925. Min Act: -0.0002

Data Index: 707639 (C4 (Web Text))

Max Activating Token Index: 450

Text #9

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3881. Min Act: -0.0002

Data Index: 1183819 (C4 (Web Text))

Max Activating Token Index: 839

Text #10

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3911. Min Act: -0.0002

Data Index: 692806 (C4 (Web Text))

Max Activating Token Index: 89

Text #11

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3882. Min Act: -0.0002

Data Index: 1232105 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3812. Min Act: -0.0002

Data Index: 881622 (C4 (Web Text))

Max Activating Token Index: 86

Text #13

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3799. Min Act: -0.0002

Data Index: 330071 (C4 (Web Text))

Max Activating Token Index: 799

Text #14

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3833. Min Act: -0.0002

Data Index: 205270 (C4 (Web Text))

Max Activating Token Index: 681

Text #15

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3844. Min Act: -0.0002

Data Index: 1300292 (C4 (Web Text))

Max Activating Token Index: 51

Text #16

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3786. Min Act: -0.0002

Data Index: 1337052 (C4 (Web Text))

Max Activating Token Index: 199

Text #17

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3702. Min Act: -0.0002

Data Index: 617627 (C4 (Web Text))

Max Activating Token Index: 91

Text #18

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3701. Min Act: -0.0002

Data Index: 589066 (C4 (Web Text))

Max Activating Token Index: 682

Text #19

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3660. Min Act: -0.0002

Data Index: 114770 (C4 (Web Text))

Max Activating Token Index: 538