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

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

Neuron 3480 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4777. Min Range: -0.4777

Max Act: 0.4777. Min Act: -0.0000

Data Index: 1079103 (C4 (Web Text))

Max Activating Token Index: 601

Text #1

Max Range: 0.4777. Min Range: -0.4777

Max Act: 0.4218. Min Act: -0.0000

Data Index: 1307040 (C4 (Web Text))

Max Activating Token Index: 387

Text #2

Max Range: 0.4777. Min Range: -0.4777

Max Act: 0.4100. Min Act: -0.0000

Data Index: 1164423 (C4 (Web Text))

Max Activating Token Index: 196

Text #3

Max Range: 0.4777. Min Range: -0.4777

Max Act: 0.3812. Min Act: -0.0000

Data Index: 106504 (C4 (Web Text))

Max Activating Token Index: 99

Text #4

Max Range: 0.4777. Min Range: -0.4777

Max Act: 0.3143. Min Act: -0.0000

Data Index: 148483 (C4 (Web Text))

Max Activating Token Index: 66

Text #5

Max Range: 0.4777. Min Range: -0.4777

Max Act: 0.3245. Min Act: -0.0000

Data Index: 1270683 (C4 (Web Text))

Max Activating Token Index: 800

Text #6

Max Range: 0.4777. Min Range: -0.4777

Max Act: 0.2911. Min Act: -0.0000

Data Index: 29044 (C4 (Web Text))

Max Activating Token Index: 158

Text #7

Max Range: 0.4777. Min Range: -0.4777

Max Act: 0.2946. Min Act: -0.0000

Data Index: 1001545 (C4 (Web Text))

Max Activating Token Index: 742

Text #8

Max Range: 0.4777. Min Range: -0.4777

Max Act: 0.2861. Min Act: -0.0000

Data Index: 588178 (C4 (Web Text))

Max Activating Token Index: 311

Text #9

Max Range: 0.4777. Min Range: -0.4777

Max Act: 0.2985. Min Act: -0.0000

Data Index: 1267470 (C4 (Web Text))

Max Activating Token Index: 471

Text #10

Max Range: 0.4777. Min Range: -0.4777

Max Act: 0.2828. Min Act: -0.0000

Data Index: 440531 (C4 (Web Text))

Max Activating Token Index: 325

Text #11

Max Range: 0.4777. Min Range: -0.4777

Max Act: 0.2701. Min Act: -0.0000

Data Index: 1109066 (C4 (Web Text))

Max Activating Token Index: 650

Text #12

Max Range: 0.4777. Min Range: -0.4777

Max Act: 0.2723. Min Act: -0.0000

Data Index: 824245 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 0.4777. Min Range: -0.4777

Max Act: 0.2509. Min Act: -0.0000

Data Index: 149988 (C4 (Web Text))

Max Activating Token Index: 813

Text #14

Max Range: 0.4777. Min Range: -0.4777

Max Act: 0.2669. Min Act: -0.0000

Data Index: 173411 (C4 (Web Text))

Max Activating Token Index: 663

Text #15

Max Range: 0.4777. Min Range: -0.4777

Max Act: 0.2734. Min Act: -0.0000

Data Index: 1272136 (C4 (Web Text))

Max Activating Token Index: 456

Text #16

Max Range: 0.4777. Min Range: -0.4777

Max Act: 0.2436. Min Act: -0.0000

Data Index: 503888 (C4 (Web Text))

Max Activating Token Index: 802

Text #17

Max Range: 0.4777. Min Range: -0.4777

Max Act: 0.2525. Min Act: -0.0000

Data Index: 413336 (C4 (Web Text))

Max Activating Token Index: 195

Text #18

Max Range: 0.4777. Min Range: -0.4777

Max Act: 0.2599. Min Act: -0.0000

Data Index: 1081958 (C4 (Web Text))

Max Activating Token Index: 429

Text #19

Max Range: 0.4777. Min Range: -0.4777

Max Act: 0.2657. Min Act: -0.0000

Data Index: 790495 (C4 (Web Text))

Max Activating Token Index: 180