Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1304 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.6960. Min Act: -0.0000

Data Index: 1256692 (C4 (Web Text))

Max Activating Token Index: 265

Text #1

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.6260. Min Act: -0.0000

Data Index: 1097988 (C4 (Web Text))

Max Activating Token Index: 611

Text #2

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.6107. Min Act: -0.0000

Data Index: 224473 (C4 (Web Text))

Max Activating Token Index: 317

Text #3

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.5702. Min Act: -0.0000

Data Index: 1168642 (C4 (Web Text))

Max Activating Token Index: 774

Text #4

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.5646. Min Act: -0.0000

Data Index: 1007602 (C4 (Web Text))

Max Activating Token Index: 466

Text #5

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.5421. Min Act: -0.0000

Data Index: 953661 (C4 (Web Text))

Max Activating Token Index: 974

Text #6

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.5164. Min Act: -0.0000

Data Index: 684783 (C4 (Web Text))

Max Activating Token Index: 457

Text #7

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.4880. Min Act: -0.0000

Data Index: 555333 (C4 (Web Text))

Max Activating Token Index: 252

Text #8

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.4652. Min Act: -0.0000

Data Index: 1075888 (C4 (Web Text))

Max Activating Token Index: 617

Text #9

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.4605. Min Act: -0.0000

Data Index: 873215 (C4 (Web Text))

Max Activating Token Index: 293

Text #10

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.4716. Min Act: -0.0000

Data Index: 195121 (C4 (Web Text))

Max Activating Token Index: 435

Text #11

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.4844. Min Act: -0.0000

Data Index: 20448 (C4 (Web Text))

Max Activating Token Index: 472

Text #12

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.4472. Min Act: 0.0000

Data Index: 1306694 (C4 (Web Text))

Max Activating Token Index: 614

Text #13

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.4516. Min Act: -0.0000

Data Index: 1163071 (C4 (Web Text))

Max Activating Token Index: 873

Text #14

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.4338. Min Act: -0.0000

Data Index: 466077 (C4 (Web Text))

Max Activating Token Index: 262

Text #15

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.4196. Min Act: -0.0000

Data Index: 148342 (C4 (Web Text))

Max Activating Token Index: 757

Text #16

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.4271. Min Act: -0.0000

Data Index: 150983 (C4 (Web Text))

Max Activating Token Index: 59

Text #17

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.4251. Min Act: -0.0000

Data Index: 986442 (C4 (Web Text))

Max Activating Token Index: 599

Text #18

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.4224. Min Act: -0.0000

Data Index: 697073 (C4 (Web Text))

Max Activating Token Index: 433

Text #19

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.4196. Min Act: -0.0000

Data Index: 443884 (C4 (Web Text))

Max Activating Token Index: 913