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

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

Neuron 3798 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: 0.3942. Min Range: -0.3942

Max Act: 0.3942. Min Act: -0.0001

Data Index: 1013644 (C4 (Web Text))

Max Activating Token Index: 95

Text #1

Max Range: 0.3942. Min Range: -0.3942

Max Act: 0.3273. Min Act: -0.0002

Data Index: 30840 (C4 (Web Text))

Max Activating Token Index: 701

Text #2

Max Range: 0.3942. Min Range: -0.3942

Max Act: 0.3349. Min Act: -0.0002

Data Index: 595153 (C4 (Web Text))

Max Activating Token Index: 674

Text #3

Max Range: 0.3942. Min Range: -0.3942

Max Act: 0.3273. Min Act: -0.0001

Data Index: 600551 (C4 (Web Text))

Max Activating Token Index: 860

Text #4

Max Range: 0.3942. Min Range: -0.3942

Max Act: 0.3051. Min Act: -0.0001

Data Index: 863440 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 0.3942. Min Range: -0.3942

Max Act: 0.2976. Min Act: -0.0001

Data Index: 1339646 (C4 (Web Text))

Max Activating Token Index: 743

Text #6

Max Range: 0.3942. Min Range: -0.3942

Max Act: 0.2986. Min Act: -0.0001

Data Index: 603058 (C4 (Web Text))

Max Activating Token Index: 229

Text #7

Max Range: 0.3942. Min Range: -0.3942

Max Act: 0.3174. Min Act: -0.0001

Data Index: 415881 (C4 (Web Text))

Max Activating Token Index: 762

Text #8

Max Range: 0.3942. Min Range: -0.3942

Max Act: 0.3010. Min Act: -0.0002

Data Index: 619304 (C4 (Web Text))

Max Activating Token Index: 298

Text #9

Max Range: 0.3942. Min Range: -0.3942

Max Act: 0.2657. Min Act: -0.0002

Data Index: 802923 (C4 (Web Text))

Max Activating Token Index: 809

Text #10

Max Range: 0.3942. Min Range: -0.3942

Max Act: 0.2743. Min Act: -0.0001

Data Index: 1018870 (C4 (Web Text))

Max Activating Token Index: 227

Text #11

Max Range: 0.3942. Min Range: -0.3942

Max Act: 0.3148. Min Act: -0.0002

Data Index: 559041 (C4 (Web Text))

Max Activating Token Index: 355

Text #12

Max Range: 0.3942. Min Range: -0.3942

Max Act: 0.3446. Min Act: -0.0001

Data Index: 1121343 (C4 (Web Text))

Max Activating Token Index: 579

Text #13

Max Range: 0.3942. Min Range: -0.3942

Max Act: 0.3075. Min Act: -0.0002

Data Index: 126160 (C4 (Web Text))

Max Activating Token Index: 489

Text #14

Max Range: 0.3942. Min Range: -0.3942

Max Act: 0.2600. Min Act: -0.0002

Data Index: 1358475 (C4 (Web Text))

Max Activating Token Index: 586

Text #15

Max Range: 0.3942. Min Range: -0.3942

Max Act: 0.2797. Min Act: -0.0001

Data Index: 989009 (C4 (Web Text))

Max Activating Token Index: 170

Text #16

Max Range: 0.3942. Min Range: -0.3942

Max Act: 0.2454. Min Act: -0.0002

Data Index: 1014767 (C4 (Web Text))

Max Activating Token Index: 743

Text #17

Max Range: 0.3942. Min Range: -0.3942

Max Act: 0.2914. Min Act: -0.0001

Data Index: 644956 (C4 (Web Text))

Max Activating Token Index: 662

Text #18

Max Range: 0.3942. Min Range: -0.3942

Max Act: 0.2721. Min Act: -0.0002

Data Index: 1160542 (C4 (Web Text))

Max Activating Token Index: 753

Text #19

Max Range: 0.3942. Min Range: -0.3942

Max Act: 0.2707. Min Act: -0.0002

Data Index: 396244 (C4 (Web Text))

Max Activating Token Index: 939