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

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

Neuron 3569 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3736. Min Range: -0.3736

Max Act: 0.3715. Min Act: -0.0001

Data Index: 578275 (C4 (Web Text))

Max Activating Token Index: 276

Text #1

Max Range: 0.3736. Min Range: -0.3736

Max Act: 0.3716. Min Act: -0.0001

Data Index: 820158 (C4 (Web Text))

Max Activating Token Index: 88

Text #2

Max Range: 0.3736. Min Range: -0.3736

Max Act: 0.3736. Min Act: -0.0001

Data Index: 879954 (C4 (Web Text))

Max Activating Token Index: 157

Text #3

Max Range: 0.3736. Min Range: -0.3736

Max Act: 0.3652. Min Act: -0.0001

Data Index: 669024 (C4 (Web Text))

Max Activating Token Index: 771

Text #4

Max Range: 0.3736. Min Range: -0.3736

Max Act: 0.3677. Min Act: -0.0001

Data Index: 847836 (C4 (Web Text))

Max Activating Token Index: 964

Text #5

Max Range: 0.3736. Min Range: -0.3736

Max Act: 0.3426. Min Act: -0.0001

Data Index: 806164 (C4 (Web Text))

Max Activating Token Index: 159

Text #6

Max Range: 0.3736. Min Range: -0.3736

Max Act: 0.3022. Min Act: -0.0001

Data Index: 1033814 (C4 (Web Text))

Max Activating Token Index: 162

Text #7

Max Range: 0.3736. Min Range: -0.3736

Max Act: 0.3172. Min Act: -0.0001

Data Index: 146280 (C4 (Web Text))

Max Activating Token Index: 65

Text #8

Max Range: 0.3736. Min Range: -0.3736

Max Act: 0.3370. Min Act: -0.0001

Data Index: 1046836 (C4 (Web Text))

Max Activating Token Index: 814

Text #9

Max Range: 0.3736. Min Range: -0.3736

Max Act: 0.3213. Min Act: -0.0001

Data Index: 1214499 (C4 (Web Text))

Max Activating Token Index: 4

Text #10

Max Range: 0.3736. Min Range: -0.3736

Max Act: 0.3071. Min Act: -0.0001

Data Index: 743731 (C4 (Web Text))

Max Activating Token Index: 832

Text #11

Max Range: 0.3736. Min Range: -0.3736

Max Act: 0.3062. Min Act: -0.0001

Data Index: 1352154 (C4 (Web Text))

Max Activating Token Index: 705

Text #12

Max Range: 0.3736. Min Range: -0.3736

Max Act: 0.3043. Min Act: -0.0001

Data Index: 114793 (C4 (Web Text))

Max Activating Token Index: 142

Text #13

Max Range: 0.3736. Min Range: -0.3736

Max Act: 0.3028. Min Act: -0.0001

Data Index: 396944 (C4 (Web Text))

Max Activating Token Index: 697

Text #14

Max Range: 0.3736. Min Range: -0.3736

Max Act: 0.3199. Min Act: -0.0001

Data Index: 1036854 (C4 (Web Text))

Max Activating Token Index: 760

Text #15

Max Range: 0.3736. Min Range: -0.3736

Max Act: 0.2991. Min Act: -0.0001

Data Index: 44262 (C4 (Web Text))

Max Activating Token Index: 597

Text #16

Max Range: 0.3736. Min Range: -0.3736

Max Act: 0.2962. Min Act: -0.0001

Data Index: 650283 (C4 (Web Text))

Max Activating Token Index: 27

Text #17

Max Range: 0.3736. Min Range: -0.3736

Max Act: 0.2863. Min Act: -0.0001

Data Index: 719290 (C4 (Web Text))

Max Activating Token Index: 833

Text #18

Max Range: 0.3736. Min Range: -0.3736

Max Act: 0.2930. Min Act: -0.0001

Data Index: 1054237 (C4 (Web Text))

Max Activating Token Index: 1022

Text #19

Max Range: 0.3736. Min Range: -0.3736

Max Act: 0.2889. Min Act: -0.0001

Data Index: 392446 (C4 (Web Text))

Max Activating Token Index: 47