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

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

Neuron 3068 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: 2.4061. Min Range: -2.4061

Max Act: 2.4061. Min Act: -0.0000

Data Index: 824038 (C4 (Web Text))

Max Activating Token Index: 249

Text #1

Max Range: 2.4061. Min Range: -2.4061

Max Act: 2.2204. Min Act: -0.0000

Data Index: 334979 (C4 (Web Text))

Max Activating Token Index: 560

Text #2

Max Range: 2.4061. Min Range: -2.4061

Max Act: 2.2821. Min Act: -0.0000

Data Index: 25648 (C4 (Web Text))

Max Activating Token Index: 273

Text #3

Max Range: 2.4061. Min Range: -2.4061

Max Act: 2.0432. Min Act: -0.0000

Data Index: 898408 (C4 (Web Text))

Max Activating Token Index: 173

Text #4

Max Range: 2.4061. Min Range: -2.4061

Max Act: 2.0318. Min Act: -0.0000

Data Index: 325556 (C4 (Web Text))

Max Activating Token Index: 914

Text #5

Max Range: 2.4061. Min Range: -2.4061

Max Act: 1.9635. Min Act: -0.0000

Data Index: 624698 (C4 (Web Text))

Max Activating Token Index: 633

Text #6

Max Range: 2.4061. Min Range: -2.4061

Max Act: 1.9526. Min Act: -0.0000

Data Index: 206678 (C4 (Web Text))

Max Activating Token Index: 798

Text #7

Max Range: 2.4061. Min Range: -2.4061

Max Act: 1.9332. Min Act: -0.0000

Data Index: 211151 (C4 (Web Text))

Max Activating Token Index: 470

Text #8

Max Range: 2.4061. Min Range: -2.4061

Max Act: 1.8879. Min Act: -0.0000

Data Index: 1170711 (C4 (Web Text))

Max Activating Token Index: 1000

Text #9

Max Range: 2.4061. Min Range: -2.4061

Max Act: 1.8933. Min Act: -0.0000

Data Index: 342432 (C4 (Web Text))

Max Activating Token Index: 905

Text #10

Max Range: 2.4061. Min Range: -2.4061

Max Act: 1.8499. Min Act: -0.0000

Data Index: 562888 (C4 (Web Text))

Max Activating Token Index: 493

Text #11

Max Range: 2.4061. Min Range: -2.4061

Max Act: 1.8387. Min Act: -0.0000

Data Index: 993619 (C4 (Web Text))

Max Activating Token Index: 668

Text #12

Max Range: 2.4061. Min Range: -2.4061

Max Act: 1.8239. Min Act: -0.0000

Data Index: 219839 (C4 (Web Text))

Max Activating Token Index: 870

Text #13

Max Range: 2.4061. Min Range: -2.4061

Max Act: 1.7138. Min Act: -0.0000

Data Index: 982054 (C4 (Web Text))

Max Activating Token Index: 538

Text #14

Max Range: 2.4061. Min Range: -2.4061

Max Act: 1.8233. Min Act: -0.0000

Data Index: 103803 (C4 (Web Text))

Max Activating Token Index: 850

Text #15

Max Range: 2.4061. Min Range: -2.4061

Max Act: 1.8232. Min Act: -0.0000

Data Index: 428140 (C4 (Web Text))

Max Activating Token Index: 173

Text #16

Max Range: 2.4061. Min Range: -2.4061

Max Act: 1.8137. Min Act: -0.0000

Data Index: 71479 (C4 (Web Text))

Max Activating Token Index: 60

Text #17

Max Range: 2.4061. Min Range: -2.4061

Max Act: 1.8097. Min Act: -0.0000

Data Index: 285068 (C4 (Web Text))

Max Activating Token Index: 995

Text #18

Max Range: 2.4061. Min Range: -2.4061

Max Act: 1.8145. Min Act: -0.0000

Data Index: 873283 (C4 (Web Text))

Max Activating Token Index: 39

Text #19

Max Range: 2.4061. Min Range: -2.4061

Max Act: 1.8717. Min Act: -0.0000

Data Index: 1029326 (C4 (Web Text))

Max Activating Token Index: 745