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

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

Neuron 4007 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.5680. Min Act: -0.0000

Data Index: 660044 (C4 (Web Text))

Max Activating Token Index: 826

Text #1

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.5607. Min Act: -0.0000

Data Index: 35391 (C4 (Web Text))

Max Activating Token Index: 279

Text #2

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.5907. Min Act: -0.0000

Data Index: 1193223 (C4 (Web Text))

Max Activating Token Index: 917

Text #3

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.5623. Min Act: -0.0000

Data Index: 383729 (C4 (Web Text))

Max Activating Token Index: 282

Text #4

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.5352. Min Act: -0.0000

Data Index: 417210 (C4 (Web Text))

Max Activating Token Index: 462

Text #5

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.5724. Min Act: -0.0000

Data Index: 1015098 (C4 (Web Text))

Max Activating Token Index: 67

Text #6

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.5472. Min Act: -0.0000

Data Index: 28052 (C4 (Web Text))

Max Activating Token Index: 299

Text #7

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4908. Min Act: -0.0000

Data Index: 350767 (C4 (Web Text))

Max Activating Token Index: 175

Text #8

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4965. Min Act: -0.0000

Data Index: 930316 (C4 (Web Text))

Max Activating Token Index: 75

Text #9

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4997. Min Act: -0.0000

Data Index: 586709 (C4 (Web Text))

Max Activating Token Index: 298

Text #10

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4871. Min Act: -0.0000

Data Index: 807253 (C4 (Web Text))

Max Activating Token Index: 355

Text #11

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4831. Min Act: -0.0000

Data Index: 356008 (C4 (Web Text))

Max Activating Token Index: 161

Text #12

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4661. Min Act: -0.0000

Data Index: 236556 (C4 (Web Text))

Max Activating Token Index: 899

Text #13

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.5109. Min Act: -0.0000

Data Index: 500689 (C4 (Web Text))

Max Activating Token Index: 895

Text #14

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4634. Min Act: -0.0000

Data Index: 962491 (C4 (Web Text))

Max Activating Token Index: 954

Text #15

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4363. Min Act: -0.0000

Data Index: 1161567 (C4 (Web Text))

Max Activating Token Index: 464

Text #16

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4639. Min Act: -0.0000

Data Index: 205242 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4611. Min Act: -0.0000

Data Index: 1331967 (C4 (Web Text))

Max Activating Token Index: 592

Text #18

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4591. Min Act: -0.0000

Data Index: 596704 (C4 (Web Text))

Max Activating Token Index: 84

Text #19

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4341. Min Act: -0.0000

Data Index: 1151571 (C4 (Web Text))

Max Activating Token Index: 77