Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1390 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4405. Min Range: -0.4405

Max Act: 0.4405. Min Act: -0.0001

Data Index: 143439 (C4 (Web Text))

Max Activating Token Index: 852

Text #1

Max Range: 0.4405. Min Range: -0.4405

Max Act: 0.4395. Min Act: -0.0000

Data Index: 1248240 (C4 (Web Text))

Max Activating Token Index: 120

Text #2

Max Range: 0.4405. Min Range: -0.4405

Max Act: 0.4336. Min Act: -0.0000

Data Index: 637479 (C4 (Web Text))

Max Activating Token Index: 769

Text #3

Max Range: 0.4405. Min Range: -0.4405

Max Act: 0.4044. Min Act: -0.0001

Data Index: 967625 (C4 (Web Text))

Max Activating Token Index: 734

Text #4

Max Range: 0.4405. Min Range: -0.4405

Max Act: 0.4134. Min Act: -0.0001

Data Index: 1332964 (C4 (Web Text))

Max Activating Token Index: 762

Text #5

Max Range: 0.4405. Min Range: -0.4405

Max Act: 0.4010. Min Act: -0.0000

Data Index: 308035 (C4 (Web Text))

Max Activating Token Index: 874

Text #6

Max Range: 0.4405. Min Range: -0.4405

Max Act: 0.3808. Min Act: -0.0000

Data Index: 393989 (C4 (Web Text))

Max Activating Token Index: 362

Text #7

Max Range: 0.4405. Min Range: -0.4405

Max Act: 0.3799. Min Act: 0.0002

Data Index: 1209965 (C4 (Web Text))

Max Activating Token Index: 541

Text #8

Max Range: 0.4405. Min Range: -0.4405

Max Act: 0.3606. Min Act: 0.0000

Data Index: 344133 (C4 (Web Text))

Max Activating Token Index: 619

Text #9

Max Range: 0.4405. Min Range: -0.4405

Max Act: 0.3844. Min Act: -0.0000

Data Index: 116736 (C4 (Web Text))

Max Activating Token Index: 63

Text #10

Max Range: 0.4405. Min Range: -0.4405

Max Act: 0.3817. Min Act: 0.0001

Data Index: 638318 (C4 (Web Text))

Max Activating Token Index: 349

Text #11

Max Range: 0.4405. Min Range: -0.4405

Max Act: 0.3817. Min Act: -0.0001

Data Index: 141042 (C4 (Web Text))

Max Activating Token Index: 759

Text #12

Max Range: 0.4405. Min Range: -0.4405

Max Act: 0.3922. Min Act: -0.0000

Data Index: 83966 (C4 (Web Text))

Max Activating Token Index: 152

Text #13

Max Range: 0.4405. Min Range: -0.4405

Max Act: 0.3666. Min Act: -0.0001

Data Index: 883803 (C4 (Web Text))

Max Activating Token Index: 435

Text #14

Max Range: 0.4405. Min Range: -0.4405

Max Act: 0.3485. Min Act: -0.0000

Data Index: 699868 (C4 (Web Text))

Max Activating Token Index: 112

Text #15

Max Range: 0.4405. Min Range: -0.4405

Max Act: 0.3726. Min Act: -0.0001

Data Index: 640029 (C4 (Web Text))

Max Activating Token Index: 163

Text #16

Max Range: 0.4405. Min Range: -0.4405

Max Act: 0.3797. Min Act: -0.0000

Data Index: 1135761 (C4 (Web Text))

Max Activating Token Index: 817

Text #17

Max Range: 0.4405. Min Range: -0.4405

Max Act: 0.3676. Min Act: -0.0000

Data Index: 1108585 (C4 (Web Text))

Max Activating Token Index: 176

Text #18

Max Range: 0.4405. Min Range: -0.4405

Max Act: 0.3546. Min Act: -0.0001

Data Index: 1013737 (C4 (Web Text))

Max Activating Token Index: 356

Text #19

Max Range: 0.4405. Min Range: -0.4405

Max Act: 0.3626. Min Act: -0.0001

Data Index: 1091051 (C4 (Web Text))

Max Activating Token Index: 78