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

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

Neuron 1243 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: 0.5830. Min Range: -0.5830

Max Act: 0.5830. Min Act: -0.0000

Data Index: 777963 (C4 (Web Text))

Max Activating Token Index: 492

Text #1

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.4946. Min Act: -0.0000

Data Index: 1183865 (C4 (Web Text))

Max Activating Token Index: 441

Text #2

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.4272. Min Act: -0.0000

Data Index: 336463 (C4 (Web Text))

Max Activating Token Index: 851

Text #3

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.4400. Min Act: -0.0000

Data Index: 134654 (C4 (Web Text))

Max Activating Token Index: 763

Text #4

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.4751. Min Act: -0.0000

Data Index: 430152 (C4 (Web Text))

Max Activating Token Index: 494

Text #5

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.4433. Min Act: -0.0000

Data Index: 242819 (C4 (Web Text))

Max Activating Token Index: 366

Text #6

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.4374. Min Act: -0.0000

Data Index: 1189414 (C4 (Web Text))

Max Activating Token Index: 374

Text #7

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.4157. Min Act: -0.0000

Data Index: 1234992 (C4 (Web Text))

Max Activating Token Index: 357

Text #8

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.4475. Min Act: -0.0000

Data Index: 1169298 (C4 (Web Text))

Max Activating Token Index: 300

Text #9

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.3997. Min Act: -0.0000

Data Index: 1241079 (C4 (Web Text))

Max Activating Token Index: 931

Text #10

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.3744. Min Act: -0.0000

Data Index: 355293 (C4 (Web Text))

Max Activating Token Index: 735

Text #11

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.3888. Min Act: -0.0000

Data Index: 1314212 (C4 (Web Text))

Max Activating Token Index: 724

Text #12

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.4033. Min Act: -0.0000

Data Index: 26010 (C4 (Web Text))

Max Activating Token Index: 782

Text #13

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.3717. Min Act: -0.0000

Data Index: 1124368 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.3957. Min Act: -0.0000

Data Index: 213966 (C4 (Web Text))

Max Activating Token Index: 71

Text #15

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.4006. Min Act: -0.0000

Data Index: 970198 (C4 (Web Text))

Max Activating Token Index: 280

Text #16

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.3639. Min Act: -0.0000

Data Index: 920320 (C4 (Web Text))

Max Activating Token Index: 368

Text #17

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.3773. Min Act: -0.0000

Data Index: 1312821 (C4 (Web Text))

Max Activating Token Index: 797

Text #18

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.3599. Min Act: -0.0000

Data Index: 1218647 (C4 (Web Text))

Max Activating Token Index: 942

Text #19

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.3514. Min Act: -0.0000

Data Index: 894351 (C4 (Web Text))

Max Activating Token Index: 614