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

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

Neuron 1726 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.4458. Min Act: -0.0000

Data Index: 827657 (C4 (Web Text))

Max Activating Token Index: 542

Text #1

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.3686. Min Act: -0.0000

Data Index: 970710 (C4 (Web Text))

Max Activating Token Index: 963

Text #2

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.3698. Min Act: -0.0000

Data Index: 651675 (C4 (Web Text))

Max Activating Token Index: 606

Text #3

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.3475. Min Act: -0.0000

Data Index: 1262572 (C4 (Web Text))

Max Activating Token Index: 272

Text #4

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.3579. Min Act: -0.0000

Data Index: 619649 (C4 (Web Text))

Max Activating Token Index: 895

Text #5

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.3412. Min Act: -0.0000

Data Index: 491423 (C4 (Web Text))

Max Activating Token Index: 850

Text #6

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.3428. Min Act: -0.0000

Data Index: 904656 (C4 (Web Text))

Max Activating Token Index: 921

Text #7

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.3544. Min Act: -0.0000

Data Index: 1245672 (C4 (Web Text))

Max Activating Token Index: 994

Text #8

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.3027. Min Act: -0.0000

Data Index: 477823 (C4 (Web Text))

Max Activating Token Index: 172

Text #9

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.3005. Min Act: -0.0000

Data Index: 910245 (C4 (Web Text))

Max Activating Token Index: 984

Text #10

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.3394. Min Act: -0.0000

Data Index: 1355687 (C4 (Web Text))

Max Activating Token Index: 558

Text #11

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.2972. Min Act: -0.0000

Data Index: 1224453 (C4 (Web Text))

Max Activating Token Index: 106

Text #12

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.3171. Min Act: -0.0000

Data Index: 1121817 (C4 (Web Text))

Max Activating Token Index: 366

Text #13

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.2981. Min Act: -0.0000

Data Index: 1046986 (C4 (Web Text))

Max Activating Token Index: 996

Text #14

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.3032. Min Act: -0.0000

Data Index: 443769 (C4 (Web Text))

Max Activating Token Index: 275

Text #15

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.2943. Min Act: -0.0000

Data Index: 1259471 (C4 (Web Text))

Max Activating Token Index: 610

Text #16

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.3331. Min Act: -0.0000

Data Index: 312108 (C4 (Web Text))

Max Activating Token Index: 173

Text #17

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.3190. Min Act: -0.0000

Data Index: 627087 (C4 (Web Text))

Max Activating Token Index: 617

Text #18

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.2964. Min Act: -0.0000

Data Index: 77668 (C4 (Web Text))

Max Activating Token Index: 726

Text #19

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.3067. Min Act: -0.0000

Data Index: 724333 (C4 (Web Text))

Max Activating Token Index: 625