Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2354 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.4061. Min Act: -0.0001

Data Index: 970138 (C4 (Web Text))

Max Activating Token Index: 579

Text #1

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.4651. Min Act: -0.0001

Data Index: 1038633 (C4 (Web Text))

Max Activating Token Index: 113

Text #2

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.4283. Min Act: -0.0001

Data Index: 455088 (C4 (Web Text))

Max Activating Token Index: 990

Text #3

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.3170. Min Act: -0.0001

Data Index: 736915 (C4 (Web Text))

Max Activating Token Index: 456

Text #4

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.2631. Min Act: -0.0001

Data Index: 762457 (C4 (Web Text))

Max Activating Token Index: 959

Text #5

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.2841. Min Act: -0.0001

Data Index: 732531 (C4 (Web Text))

Max Activating Token Index: 918

Text #6

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.3233. Min Act: -0.0001

Data Index: 924711 (C4 (Web Text))

Max Activating Token Index: 488

Text #7

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.2975. Min Act: -0.0001

Data Index: 901685 (C4 (Web Text))

Max Activating Token Index: 424

Text #8

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.3430. Min Act: -0.0001

Data Index: 1163790 (C4 (Web Text))

Max Activating Token Index: 548

Text #9

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.2979. Min Act: -0.0001

Data Index: 505328 (C4 (Web Text))

Max Activating Token Index: 219

Text #10

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.3646. Min Act: -0.0001

Data Index: 1150270 (C4 (Web Text))

Max Activating Token Index: 959

Text #11

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.3184. Min Act: -0.0000

Data Index: 80245 (C4 (Web Text))

Max Activating Token Index: 676

Text #12

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.2651. Min Act: -0.0001

Data Index: 1259793 (C4 (Web Text))

Max Activating Token Index: 998

Text #13

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.2581. Min Act: -0.0001

Data Index: 670914 (C4 (Web Text))

Max Activating Token Index: 928

Text #14

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.2517. Min Act: -0.0001

Data Index: 1208332 (C4 (Web Text))

Max Activating Token Index: 61

Text #15

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.2073. Min Act: -0.0001

Data Index: 503235 (C4 (Web Text))

Max Activating Token Index: 694

Text #16

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.2020. Min Act: -0.0001

Data Index: 394498 (C4 (Web Text))

Max Activating Token Index: 649

Text #17

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.2309. Min Act: -0.0001

Data Index: 370049 (C4 (Web Text))

Max Activating Token Index: 380

Text #18

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.1880. Min Act: -0.0001

Data Index: 1133909 (C4 (Web Text))

Max Activating Token Index: 729

Text #19

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.2095. Min Act: -0.0001

Data Index: 397296 (C4 (Web Text))

Max Activating Token Index: 952