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

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

Neuron 4413 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0329. Min Range: -2.0329

Max Act: 2.0329. Min Act: -0.0000

Data Index: 675309 (C4 (Web Text))

Max Activating Token Index: 969

Text #1

Max Range: 2.0329. Min Range: -2.0329

Max Act: 1.9046. Min Act: -0.0000

Data Index: 590324 (C4 (Web Text))

Max Activating Token Index: 959

Text #2

Max Range: 2.0329. Min Range: -2.0329

Max Act: 1.7738. Min Act: -0.0000

Data Index: 304489 (C4 (Web Text))

Max Activating Token Index: 397

Text #3

Max Range: 2.0329. Min Range: -2.0329

Max Act: 1.5831. Min Act: -0.0000

Data Index: 402788 (C4 (Web Text))

Max Activating Token Index: 313

Text #4

Max Range: 2.0329. Min Range: -2.0329

Max Act: 1.4796. Min Act: -0.0000

Data Index: 933085 (C4 (Web Text))

Max Activating Token Index: 498

Text #5

Max Range: 2.0329. Min Range: -2.0329

Max Act: 1.4764. Min Act: -0.0000

Data Index: 814530 (C4 (Web Text))

Max Activating Token Index: 418

Text #6

Max Range: 2.0329. Min Range: -2.0329

Max Act: 1.3498. Min Act: -0.0000

Data Index: 854464 (C4 (Web Text))

Max Activating Token Index: 735

Text #7

Max Range: 2.0329. Min Range: -2.0329

Max Act: 1.3402. Min Act: -0.0000

Data Index: 788479 (C4 (Web Text))

Max Activating Token Index: 839

Text #8

Max Range: 2.0329. Min Range: -2.0329

Max Act: 1.3422. Min Act: -0.0000

Data Index: 256023 (C4 (Web Text))

Max Activating Token Index: 713

Text #9

Max Range: 2.0329. Min Range: -2.0329

Max Act: 1.4192. Min Act: -0.0000

Data Index: 257497 (C4 (Web Text))

Max Activating Token Index: 205

Text #10

Max Range: 2.0329. Min Range: -2.0329

Max Act: 1.4145. Min Act: -0.0000

Data Index: 58556 (C4 (Web Text))

Max Activating Token Index: 572

Text #11

Max Range: 2.0329. Min Range: -2.0329

Max Act: 1.3232. Min Act: -0.0000

Data Index: 1359761 (C4 (Web Text))

Max Activating Token Index: 749

Text #12

Max Range: 2.0329. Min Range: -2.0329

Max Act: 1.3059. Min Act: -0.0000

Data Index: 896280 (C4 (Web Text))

Max Activating Token Index: 564

Text #13

Max Range: 2.0329. Min Range: -2.0329

Max Act: 1.3050. Min Act: -0.0000

Data Index: 1152766 (C4 (Web Text))

Max Activating Token Index: 586

Text #14

Max Range: 2.0329. Min Range: -2.0329

Max Act: 1.2818. Min Act: -0.0000

Data Index: 380002 (C4 (Web Text))

Max Activating Token Index: 133

Text #15

Max Range: 2.0329. Min Range: -2.0329

Max Act: 1.2554. Min Act: -0.0000

Data Index: 1205097 (C4 (Web Text))

Max Activating Token Index: 286

Text #16

Max Range: 2.0329. Min Range: -2.0329

Max Act: 1.2619. Min Act: -0.0000

Data Index: 1156754 (C4 (Web Text))

Max Activating Token Index: 697

Text #17

Max Range: 2.0329. Min Range: -2.0329

Max Act: 1.2528. Min Act: -0.0000

Data Index: 1150309 (C4 (Web Text))

Max Activating Token Index: 39

Text #18

Max Range: 2.0329. Min Range: -2.0329

Max Act: 1.2339. Min Act: -0.0000

Data Index: 70301 (C4 (Web Text))

Max Activating Token Index: 496

Text #19

Max Range: 2.0329. Min Range: -2.0329

Max Act: 1.2165. Min Act: -0.0000

Data Index: 1177377 (C4 (Web Text))

Max Activating Token Index: 645