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

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

Neuron 1114 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: 0.6764. Min Range: -0.6764

Max Act: 0.6764. Min Act: -0.0002

Data Index: 1297431 (C4 (Web Text))

Max Activating Token Index: 899

Text #1

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.6341. Min Act: -0.0002

Data Index: 568939 (C4 (Web Text))

Max Activating Token Index: 244

Text #2

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.6311. Min Act: -0.0002

Data Index: 378055 (C4 (Web Text))

Max Activating Token Index: 998

Text #3

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.6069. Min Act: -0.0002

Data Index: 316019 (C4 (Web Text))

Max Activating Token Index: 766

Text #4

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.6004. Min Act: -0.0002

Data Index: 1196368 (C4 (Web Text))

Max Activating Token Index: 362

Text #5

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.6048. Min Act: -0.0002

Data Index: 142650 (C4 (Web Text))

Max Activating Token Index: 386

Text #6

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.5919. Min Act: -0.0002

Data Index: 377141 (C4 (Web Text))

Max Activating Token Index: 996

Text #7

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.6083. Min Act: -0.0002

Data Index: 225150 (C4 (Web Text))

Max Activating Token Index: 998

Text #8

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.5897. Min Act: -0.0002

Data Index: 11467 (C4 (Web Text))

Max Activating Token Index: 919

Text #9

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.5831. Min Act: -0.0002

Data Index: 394734 (C4 (Web Text))

Max Activating Token Index: 372

Text #10

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.5748. Min Act: -0.0002

Data Index: 1220196 (C4 (Web Text))

Max Activating Token Index: 597

Text #11

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.5812. Min Act: -0.0002

Data Index: 83757 (C4 (Web Text))

Max Activating Token Index: 899

Text #12

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.5759. Min Act: -0.0002

Data Index: 900470 (C4 (Web Text))

Max Activating Token Index: 634

Text #13

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.5747. Min Act: -0.0002

Data Index: 957378 (C4 (Web Text))

Max Activating Token Index: 875

Text #14

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.5743. Min Act: -0.0002

Data Index: 1139961 (C4 (Web Text))

Max Activating Token Index: 576

Text #15

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.5752. Min Act: -0.0002

Data Index: 739908 (C4 (Web Text))

Max Activating Token Index: 288

Text #16

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.5818. Min Act: -0.0002

Data Index: 270143 (C4 (Web Text))

Max Activating Token Index: 998

Text #17

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.5715. Min Act: -0.0002

Data Index: 644116 (C4 (Web Text))

Max Activating Token Index: 152

Text #18

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.5716. Min Act: -0.0002

Data Index: 744168 (C4 (Web Text))

Max Activating Token Index: 223

Text #19

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.5658. Min Act: -0.0002

Data Index: 659806 (C4 (Web Text))

Max Activating Token Index: 956