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

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

Neuron 1684 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4062. Min Range: -0.4062

Max Act: 0.4062. Min Act: -0.0001

Data Index: 180862 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 0.4062. Min Range: -0.4062

Max Act: 0.3688. Min Act: -0.0001

Data Index: 42858 (C4 (Web Text))

Max Activating Token Index: 705

Text #2

Max Range: 0.4062. Min Range: -0.4062

Max Act: 0.3716. Min Act: -0.0001

Data Index: 648586 (C4 (Web Text))

Max Activating Token Index: 615

Text #3

Max Range: 0.4062. Min Range: -0.4062

Max Act: 0.3653. Min Act: -0.0001

Data Index: 1012699 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 0.4062. Min Range: -0.4062

Max Act: 0.3362. Min Act: -0.0001

Data Index: 1175852 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 0.4062. Min Range: -0.4062

Max Act: 0.3492. Min Act: -0.0001

Data Index: 1266149 (C4 (Web Text))

Max Activating Token Index: 440

Text #6

Max Range: 0.4062. Min Range: -0.4062

Max Act: 0.3315. Min Act: -0.0001

Data Index: 982545 (C4 (Web Text))

Max Activating Token Index: 768

Text #7

Max Range: 0.4062. Min Range: -0.4062

Max Act: 0.3612. Min Act: -0.0001

Data Index: 758810 (C4 (Web Text))

Max Activating Token Index: 288

Text #8

Max Range: 0.4062. Min Range: -0.4062

Max Act: 0.3191. Min Act: -0.0001

Data Index: 974847 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 0.4062. Min Range: -0.4062

Max Act: 0.3133. Min Act: -0.0001

Data Index: 1012870 (C4 (Web Text))

Max Activating Token Index: 490

Text #10

Max Range: 0.4062. Min Range: -0.4062

Max Act: 0.3215. Min Act: -0.0001

Data Index: 814573 (C4 (Web Text))

Max Activating Token Index: 185

Text #11

Max Range: 0.4062. Min Range: -0.4062

Max Act: 0.3011. Min Act: -0.0001

Data Index: 771472 (C4 (Web Text))

Max Activating Token Index: 509

Text #12

Max Range: 0.4062. Min Range: -0.4062

Max Act: 0.3214. Min Act: -0.0001

Data Index: 878938 (C4 (Web Text))

Max Activating Token Index: 531

Text #13

Max Range: 0.4062. Min Range: -0.4062

Max Act: 0.3077. Min Act: -0.0001

Data Index: 768790 (C4 (Web Text))

Max Activating Token Index: 423

Text #14

Max Range: 0.4062. Min Range: -0.4062

Max Act: 0.2930. Min Act: -0.0001

Data Index: 712810 (C4 (Web Text))

Max Activating Token Index: 175

Text #15

Max Range: 0.4062. Min Range: -0.4062

Max Act: 0.2835. Min Act: -0.0001

Data Index: 1347093 (C4 (Web Text))

Max Activating Token Index: 11

Text #16

Max Range: 0.4062. Min Range: -0.4062

Max Act: 0.3073. Min Act: -0.0001

Data Index: 1107301 (C4 (Web Text))

Max Activating Token Index: 578

Text #17

Max Range: 0.4062. Min Range: -0.4062

Max Act: 0.3175. Min Act: -0.0001

Data Index: 38496 (C4 (Web Text))

Max Activating Token Index: 903

Text #18

Max Range: 0.4062. Min Range: -0.4062

Max Act: 0.3168. Min Act: -0.0001

Data Index: 297847 (C4 (Web Text))

Max Activating Token Index: 627

Text #19

Max Range: 0.4062. Min Range: -0.4062

Max Act: 0.2943. Min Act: -0.0001

Data Index: 698107 (C4 (Web Text))

Max Activating Token Index: 833