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

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

Neuron 4648 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6530. Min Range: -0.6530

Max Act: 0.6530. Min Act: -0.0000

Data Index: 1092270 (C4 (Web Text))

Max Activating Token Index: 507

Text #1

Max Range: 0.6530. Min Range: -0.6530

Max Act: 0.3929. Min Act: -0.0000

Data Index: 494244 (C4 (Web Text))

Max Activating Token Index: 13

Text #2

Max Range: 0.6530. Min Range: -0.6530

Max Act: 0.3656. Min Act: -0.0000

Data Index: 76 (C4 (Web Text))

Max Activating Token Index: 201

Text #3

Max Range: 0.6530. Min Range: -0.6530

Max Act: 0.3516. Min Act: 0.0000

Data Index: 409033 (C4 (Web Text))

Max Activating Token Index: 201

Text #4

Max Range: 0.6530. Min Range: -0.6530

Max Act: 0.3403. Min Act: -0.0000

Data Index: 1107986 (C4 (Web Text))

Max Activating Token Index: 824

Text #5

Max Range: 0.6530. Min Range: -0.6530

Max Act: 0.3450. Min Act: -0.0000

Data Index: 566987 (C4 (Web Text))

Max Activating Token Index: 68

Text #6

Max Range: 0.6530. Min Range: -0.6530

Max Act: 0.3278. Min Act: 0.0000

Data Index: 1131965 (C4 (Web Text))

Max Activating Token Index: 354

Text #7

Max Range: 0.6530. Min Range: -0.6530

Max Act: 0.3142. Min Act: -0.0000

Data Index: 605815 (C4 (Web Text))

Max Activating Token Index: 421

Text #8

Max Range: 0.6530. Min Range: -0.6530

Max Act: 0.3240. Min Act: -0.0000

Data Index: 644658 (C4 (Web Text))

Max Activating Token Index: 975

Text #9

Max Range: 0.6530. Min Range: -0.6530

Max Act: 0.3172. Min Act: -0.0000

Data Index: 563961 (C4 (Web Text))

Max Activating Token Index: 373

Text #10

Max Range: 0.6530. Min Range: -0.6530

Max Act: 0.3073. Min Act: -0.0000

Data Index: 1030358 (C4 (Web Text))

Max Activating Token Index: 642

Text #11

Max Range: 0.6530. Min Range: -0.6530

Max Act: 0.2994. Min Act: -0.0000

Data Index: 1156778 (C4 (Web Text))

Max Activating Token Index: 446

Text #12

Max Range: 0.6530. Min Range: -0.6530

Max Act: 0.2957. Min Act: -0.0000

Data Index: 1173066 (C4 (Web Text))

Max Activating Token Index: 774

Text #13

Max Range: 0.6530. Min Range: -0.6530

Max Act: 0.2947. Min Act: -0.0000

Data Index: 999486 (C4 (Web Text))

Max Activating Token Index: 378

Text #14

Max Range: 0.6530. Min Range: -0.6530

Max Act: 0.2828. Min Act: -0.0000

Data Index: 760576 (C4 (Web Text))

Max Activating Token Index: 371

Text #15

Max Range: 0.6530. Min Range: -0.6530

Max Act: 0.2735. Min Act: -0.0000

Data Index: 120533 (C4 (Web Text))

Max Activating Token Index: 821

Text #16

Max Range: 0.6530. Min Range: -0.6530

Max Act: 0.2970. Min Act: -0.0000

Data Index: 663525 (C4 (Web Text))

Max Activating Token Index: 827

Text #17

Max Range: 0.6530. Min Range: -0.6530

Max Act: 0.2855. Min Act: -0.0000

Data Index: 840161 (C4 (Web Text))

Max Activating Token Index: 684

Text #18

Max Range: 0.6530. Min Range: -0.6530

Max Act: 0.2839. Min Act: -0.0000

Data Index: 776213 (C4 (Web Text))

Max Activating Token Index: 337

Text #19

Max Range: 0.6530. Min Range: -0.6530

Max Act: 0.2737. Min Act: -0.0000

Data Index: 1135460 (C4 (Web Text))

Max Activating Token Index: 333