Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5575 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2969. Min Range: -1.2969

Max Act: 1.2969. Min Act: -0.0000

Data Index: 668331 (C4 (Web Text))

Max Activating Token Index: 708

Text #1

Max Range: 1.2969. Min Range: -1.2969

Max Act: 1.2387. Min Act: -0.0000

Data Index: 532552 (C4 (Web Text))

Max Activating Token Index: 576

Text #2

Max Range: 1.2969. Min Range: -1.2969

Max Act: 1.2111. Min Act: -0.0000

Data Index: 991483 (C4 (Web Text))

Max Activating Token Index: 412

Text #3

Max Range: 1.2969. Min Range: -1.2969

Max Act: 1.1585. Min Act: -0.0000

Data Index: 905275 (C4 (Web Text))

Max Activating Token Index: 970

Text #4

Max Range: 1.2969. Min Range: -1.2969

Max Act: 1.1849. Min Act: -0.0000

Data Index: 1259943 (C4 (Web Text))

Max Activating Token Index: 713

Text #5

Max Range: 1.2969. Min Range: -1.2969

Max Act: 1.0712. Min Act: -0.0000

Data Index: 1137713 (C4 (Web Text))

Max Activating Token Index: 286

Text #6

Max Range: 1.2969. Min Range: -1.2969

Max Act: 1.1132. Min Act: -0.0000

Data Index: 1040123 (C4 (Web Text))

Max Activating Token Index: 829

Text #7

Max Range: 1.2969. Min Range: -1.2969

Max Act: 1.0470. Min Act: -0.0000

Data Index: 1115750 (C4 (Web Text))

Max Activating Token Index: 630

Text #8

Max Range: 1.2969. Min Range: -1.2969

Max Act: 1.0977. Min Act: -0.0000

Data Index: 1284838 (C4 (Web Text))

Max Activating Token Index: 717

Text #9

Max Range: 1.2969. Min Range: -1.2969

Max Act: 1.0485. Min Act: -0.0000

Data Index: 518479 (C4 (Web Text))

Max Activating Token Index: 980

Text #10

Max Range: 1.2969. Min Range: -1.2969

Max Act: 1.0948. Min Act: -0.0000

Data Index: 1273877 (C4 (Web Text))

Max Activating Token Index: 473

Text #11

Max Range: 1.2969. Min Range: -1.2969

Max Act: 1.0521. Min Act: -0.0000

Data Index: 1197800 (C4 (Web Text))

Max Activating Token Index: 796

Text #12

Max Range: 1.2969. Min Range: -1.2969

Max Act: 1.0445. Min Act: -0.0000

Data Index: 1152671 (C4 (Web Text))

Max Activating Token Index: 857

Text #13

Max Range: 1.2969. Min Range: -1.2969

Max Act: 1.0250. Min Act: -0.0000

Data Index: 773339 (C4 (Web Text))

Max Activating Token Index: 842

Text #14

Max Range: 1.2969. Min Range: -1.2969

Max Act: 1.0521. Min Act: -0.0000

Data Index: 402988 (C4 (Web Text))

Max Activating Token Index: 880

Text #15

Max Range: 1.2969. Min Range: -1.2969

Max Act: 1.0866. Min Act: -0.0000

Data Index: 776726 (C4 (Web Text))

Max Activating Token Index: 285

Text #16

Max Range: 1.2969. Min Range: -1.2969

Max Act: 1.0444. Min Act: -0.0000

Data Index: 650120 (C4 (Web Text))

Max Activating Token Index: 946

Text #17

Max Range: 1.2969. Min Range: -1.2969

Max Act: 0.9783. Min Act: -0.0000

Data Index: 344667 (C4 (Web Text))

Max Activating Token Index: 465

Text #18

Max Range: 1.2969. Min Range: -1.2969

Max Act: 1.0166. Min Act: -0.0000

Data Index: 666329 (C4 (Web Text))

Max Activating Token Index: 428

Text #19

Max Range: 1.2969. Min Range: -1.2969

Max Act: 1.0073. Min Act: -0.0000

Data Index: 701115 (C4 (Web Text))

Max Activating Token Index: 486