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

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

Neuron 1259 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4705. Min Range: -0.4705

Max Act: 0.4705. Min Act: -0.0002

Data Index: 653098 (C4 (Web Text))

Max Activating Token Index: 80

Text #1

Max Range: 0.4705. Min Range: -0.4705

Max Act: 0.3901. Min Act: -0.0001

Data Index: 243544 (C4 (Web Text))

Max Activating Token Index: 542

Text #2

Max Range: 0.4705. Min Range: -0.4705

Max Act: 0.4148. Min Act: -0.0002

Data Index: 23030 (C4 (Web Text))

Max Activating Token Index: 904

Text #3

Max Range: 0.4705. Min Range: -0.4705

Max Act: 0.3702. Min Act: -0.0001

Data Index: 91284 (C4 (Web Text))

Max Activating Token Index: 835

Text #4

Max Range: 0.4705. Min Range: -0.4705

Max Act: 0.3955. Min Act: -0.0002

Data Index: 1298382 (C4 (Web Text))

Max Activating Token Index: 815

Text #5

Max Range: 0.4705. Min Range: -0.4705

Max Act: 0.3810. Min Act: -0.0002

Data Index: 1180724 (C4 (Web Text))

Max Activating Token Index: 837

Text #6

Max Range: 0.4705. Min Range: -0.4705

Max Act: 0.3799. Min Act: -0.0002

Data Index: 521393 (C4 (Web Text))

Max Activating Token Index: 198

Text #7

Max Range: 0.4705. Min Range: -0.4705

Max Act: 0.3760. Min Act: -0.0002

Data Index: 472471 (C4 (Web Text))

Max Activating Token Index: 245

Text #8

Max Range: 0.4705. Min Range: -0.4705

Max Act: 0.3744. Min Act: -0.0002

Data Index: 374358 (C4 (Web Text))

Max Activating Token Index: 41

Text #9

Max Range: 0.4705. Min Range: -0.4705

Max Act: 0.3869. Min Act: -0.0002

Data Index: 179483 (C4 (Web Text))

Max Activating Token Index: 863

Text #10

Max Range: 0.4705. Min Range: -0.4705

Max Act: 0.3560. Min Act: -0.0001

Data Index: 1291866 (C4 (Web Text))

Max Activating Token Index: 668

Text #11

Max Range: 0.4705. Min Range: -0.4705

Max Act: 0.3552. Min Act: -0.0002

Data Index: 683064 (C4 (Web Text))

Max Activating Token Index: 228

Text #12

Max Range: 0.4705. Min Range: -0.4705

Max Act: 0.3665. Min Act: -0.0001

Data Index: 572830 (C4 (Web Text))

Max Activating Token Index: 400

Text #13

Max Range: 0.4705. Min Range: -0.4705

Max Act: 0.3776. Min Act: -0.0001

Data Index: 1352300 (C4 (Web Text))

Max Activating Token Index: 1007

Text #14

Max Range: 0.4705. Min Range: -0.4705

Max Act: 0.3734. Min Act: -0.0001

Data Index: 807241 (C4 (Web Text))

Max Activating Token Index: 810

Text #15

Max Range: 0.4705. Min Range: -0.4705

Max Act: 0.3505. Min Act: -0.0001

Data Index: 1297354 (C4 (Web Text))

Max Activating Token Index: 981

Text #16

Max Range: 0.4705. Min Range: -0.4705

Max Act: 0.3323. Min Act: -0.0001

Data Index: 528840 (C4 (Web Text))

Max Activating Token Index: 776

Text #17

Max Range: 0.4705. Min Range: -0.4705

Max Act: 0.3565. Min Act: -0.0002

Data Index: 660830 (C4 (Web Text))

Max Activating Token Index: 314

Text #18

Max Range: 0.4705. Min Range: -0.4705

Max Act: 0.3449. Min Act: -0.0002

Data Index: 295818 (C4 (Web Text))

Max Activating Token Index: 719

Text #19

Max Range: 0.4705. Min Range: -0.4705

Max Act: 0.3531. Min Act: -0.0002

Data Index: 445421 (C4 (Web Text))

Max Activating Token Index: 32