Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3545 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0422. Min Range: -1.0422

Max Act: 1.0205. Min Act: -0.0001

Data Index: 1138758 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 1.0422. Min Range: -1.0422

Max Act: 1.0156. Min Act: -0.0001

Data Index: 1004137 (C4 (Web Text))

Max Activating Token Index: 445

Text #2

Max Range: 1.0422. Min Range: -1.0422

Max Act: 1.0145. Min Act: -0.0001

Data Index: 1025998 (C4 (Web Text))

Max Activating Token Index: 825

Text #3

Max Range: 1.0422. Min Range: -1.0422

Max Act: 1.0422. Min Act: -0.0001

Data Index: 739396 (C4 (Web Text))

Max Activating Token Index: 321

Text #4

Max Range: 1.0422. Min Range: -1.0422

Max Act: 0.9745. Min Act: -0.0001

Data Index: 427586 (C4 (Web Text))

Max Activating Token Index: 855

Text #5

Max Range: 1.0422. Min Range: -1.0422

Max Act: 0.9227. Min Act: -0.0001

Data Index: 1288987 (C4 (Web Text))

Max Activating Token Index: 530

Text #6

Max Range: 1.0422. Min Range: -1.0422

Max Act: 0.9316. Min Act: -0.0001

Data Index: 744661 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 1.0422. Min Range: -1.0422

Max Act: 0.9608. Min Act: -0.0001

Data Index: 1086822 (C4 (Web Text))

Max Activating Token Index: 875

Text #8

Max Range: 1.0422. Min Range: -1.0422

Max Act: 0.9410. Min Act: -0.0001

Data Index: 841767 (C4 (Web Text))

Max Activating Token Index: 578

Text #9

Max Range: 1.0422. Min Range: -1.0422

Max Act: 0.9881. Min Act: -0.0001

Data Index: 1011852 (C4 (Web Text))

Max Activating Token Index: 674

Text #10

Max Range: 1.0422. Min Range: -1.0422

Max Act: 0.8891. Min Act: -0.0001

Data Index: 240240 (C4 (Web Text))

Max Activating Token Index: 1003

Text #11

Max Range: 1.0422. Min Range: -1.0422

Max Act: 0.9877. Min Act: -0.0001

Data Index: 482036 (C4 (Web Text))

Max Activating Token Index: 849

Text #12

Max Range: 1.0422. Min Range: -1.0422

Max Act: 0.8956. Min Act: -0.0001

Data Index: 4688 (C4 (Web Text))

Max Activating Token Index: 374

Text #13

Max Range: 1.0422. Min Range: -1.0422

Max Act: 0.9161. Min Act: -0.0001

Data Index: 938147 (C4 (Web Text))

Max Activating Token Index: 629

Text #14

Max Range: 1.0422. Min Range: -1.0422

Max Act: 0.8584. Min Act: -0.0001

Data Index: 936067 (C4 (Web Text))

Max Activating Token Index: 266

Text #15

Max Range: 1.0422. Min Range: -1.0422

Max Act: 0.8784. Min Act: -0.0001

Data Index: 494166 (C4 (Web Text))

Max Activating Token Index: 778

Text #16

Max Range: 1.0422. Min Range: -1.0422

Max Act: 0.8495. Min Act: -0.0001

Data Index: 614763 (C4 (Web Text))

Max Activating Token Index: 200

Text #17

Max Range: 1.0422. Min Range: -1.0422

Max Act: 0.9314. Min Act: -0.0001

Data Index: 77567 (C4 (Web Text))

Max Activating Token Index: 296

Text #18

Max Range: 1.0422. Min Range: -1.0422

Max Act: 0.7640. Min Act: -0.0001

Data Index: 969418 (C4 (Web Text))

Max Activating Token Index: 523

Text #19

Max Range: 1.0422. Min Range: -1.0422

Max Act: 0.8972. Min Act: -0.0001

Data Index: 1230660 (C4 (Web Text))

Max Activating Token Index: 17