Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4879 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.9213. Min Range: -2.9213

Max Act: 2.9213. Min Act: -0.0000

Data Index: 911540 (C4 (Web Text))

Max Activating Token Index: 159

Text #1

Max Range: 2.9213. Min Range: -2.9213

Max Act: 2.7126. Min Act: -0.0000

Data Index: 715363 (C4 (Web Text))

Max Activating Token Index: 573

Text #2

Max Range: 2.9213. Min Range: -2.9213

Max Act: 2.5733. Min Act: -0.0000

Data Index: 895557 (C4 (Web Text))

Max Activating Token Index: 215

Text #3

Max Range: 2.9213. Min Range: -2.9213

Max Act: 2.5307. Min Act: -0.0000

Data Index: 428761 (C4 (Web Text))

Max Activating Token Index: 536

Text #4

Max Range: 2.9213. Min Range: -2.9213

Max Act: 2.4029. Min Act: -0.0000

Data Index: 1169455 (C4 (Web Text))

Max Activating Token Index: 464

Text #5

Max Range: 2.9213. Min Range: -2.9213

Max Act: 2.3600. Min Act: -0.0000

Data Index: 1265609 (C4 (Web Text))

Max Activating Token Index: 395

Text #6

Max Range: 2.9213. Min Range: -2.9213

Max Act: 2.1772. Min Act: -0.0000

Data Index: 579075 (C4 (Web Text))

Max Activating Token Index: 369

Text #7

Max Range: 2.9213. Min Range: -2.9213

Max Act: 2.2887. Min Act: -0.0000

Data Index: 168757 (C4 (Web Text))

Max Activating Token Index: 558

Text #8

Max Range: 2.9213. Min Range: -2.9213

Max Act: 2.2504. Min Act: -0.0000

Data Index: 208761 (C4 (Web Text))

Max Activating Token Index: 1000

Text #9

Max Range: 2.9213. Min Range: -2.9213

Max Act: 2.1356. Min Act: -0.0000

Data Index: 74051 (C4 (Web Text))

Max Activating Token Index: 656

Text #10

Max Range: 2.9213. Min Range: -2.9213

Max Act: 2.3591. Min Act: -0.0000

Data Index: 971063 (C4 (Web Text))

Max Activating Token Index: 931

Text #11

Max Range: 2.9213. Min Range: -2.9213

Max Act: 2.1942. Min Act: -0.0000

Data Index: 1086997 (C4 (Web Text))

Max Activating Token Index: 236

Text #12

Max Range: 2.9213. Min Range: -2.9213

Max Act: 2.1792. Min Act: -0.0000

Data Index: 1217323 (C4 (Web Text))

Max Activating Token Index: 213

Text #13

Max Range: 2.9213. Min Range: -2.9213

Max Act: 2.1875. Min Act: -0.0000

Data Index: 686556 (C4 (Web Text))

Max Activating Token Index: 298

Text #14

Max Range: 2.9213. Min Range: -2.9213

Max Act: 2.1275. Min Act: -0.0000

Data Index: 341866 (C4 (Web Text))

Max Activating Token Index: 913

Text #15

Max Range: 2.9213. Min Range: -2.9213

Max Act: 2.1166. Min Act: -0.0000

Data Index: 471674 (C4 (Web Text))

Max Activating Token Index: 175

Text #16

Max Range: 2.9213. Min Range: -2.9213

Max Act: 2.1952. Min Act: -0.0000

Data Index: 561125 (C4 (Web Text))

Max Activating Token Index: 970

Text #17

Max Range: 2.9213. Min Range: -2.9213

Max Act: 2.0787. Min Act: -0.0000

Data Index: 214951 (C4 (Web Text))

Max Activating Token Index: 883

Text #18

Max Range: 2.9213. Min Range: -2.9213

Max Act: 2.0289. Min Act: -0.0000

Data Index: 72447 (C4 (Web Text))

Max Activating Token Index: 214

Text #19

Max Range: 2.9213. Min Range: -2.9213

Max Act: 2.0506. Min Act: -0.0000

Data Index: 557374 (C4 (Web Text))

Max Activating Token Index: 440