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

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

Neuron 1705 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7767. Min Range: -3.7767

Max Act: 3.6883. Min Act: -0.0000

Data Index: 25881 (C4 (Web Text))

Max Activating Token Index: 793

Text #1

Max Range: 3.7767. Min Range: -3.7767

Max Act: 3.7313. Min Act: -0.0000

Data Index: 556012 (C4 (Web Text))

Max Activating Token Index: 316

Text #2

Max Range: 3.7767. Min Range: -3.7767

Max Act: 3.6947. Min Act: -0.0000

Data Index: 745238 (C4 (Web Text))

Max Activating Token Index: 246

Text #3

Max Range: 3.7767. Min Range: -3.7767

Max Act: 3.6672. Min Act: -0.0000

Data Index: 1056475 (C4 (Web Text))

Max Activating Token Index: 606

Text #4

Max Range: 3.7767. Min Range: -3.7767

Max Act: 3.6495. Min Act: -0.0000

Data Index: 729504 (C4 (Web Text))

Max Activating Token Index: 154

Text #5

Max Range: 3.7767. Min Range: -3.7767

Max Act: 3.7767. Min Act: -0.0000

Data Index: 1184310 (C4 (Web Text))

Max Activating Token Index: 111

Text #6

Max Range: 3.7767. Min Range: -3.7767

Max Act: 3.5789. Min Act: -0.0000

Data Index: 501746 (C4 (Web Text))

Max Activating Token Index: 615

Text #7

Max Range: 3.7767. Min Range: -3.7767

Max Act: 3.4951. Min Act: -0.0000

Data Index: 367272 (C4 (Web Text))

Max Activating Token Index: 540

Text #8

Max Range: 3.7767. Min Range: -3.7767

Max Act: 3.4989. Min Act: -0.0000

Data Index: 214450 (C4 (Web Text))

Max Activating Token Index: 5

Text #9

Max Range: 3.7767. Min Range: -3.7767

Max Act: 3.4779. Min Act: -0.0000

Data Index: 1287252 (C4 (Web Text))

Max Activating Token Index: 166

Text #10

Max Range: 3.7767. Min Range: -3.7767

Max Act: 3.3391. Min Act: -0.0000

Data Index: 804941 (C4 (Web Text))

Max Activating Token Index: 488

Text #11

Max Range: 3.7767. Min Range: -3.7767

Max Act: 3.3309. Min Act: -0.0000

Data Index: 133972 (C4 (Web Text))

Max Activating Token Index: 640

Text #12

Max Range: 3.7767. Min Range: -3.7767

Max Act: 3.4613. Min Act: -0.0000

Data Index: 753423 (C4 (Web Text))

Max Activating Token Index: 780

Text #13

Max Range: 3.7767. Min Range: -3.7767

Max Act: 3.4854. Min Act: -0.0000

Data Index: 216145 (C4 (Web Text))

Max Activating Token Index: 174

Text #14

Max Range: 3.7767. Min Range: -3.7767

Max Act: 3.3022. Min Act: -0.0000

Data Index: 897585 (C4 (Web Text))

Max Activating Token Index: 16

Text #15

Max Range: 3.7767. Min Range: -3.7767

Max Act: 3.4774. Min Act: -0.0000

Data Index: 267295 (C4 (Web Text))

Max Activating Token Index: 597

Text #16

Max Range: 3.7767. Min Range: -3.7767

Max Act: 3.4511. Min Act: -0.0000

Data Index: 878371 (C4 (Web Text))

Max Activating Token Index: 54

Text #17

Max Range: 3.7767. Min Range: -3.7767

Max Act: 3.2826. Min Act: -0.0000

Data Index: 800262 (C4 (Web Text))

Max Activating Token Index: 798

Text #18

Max Range: 3.7767. Min Range: -3.7767

Max Act: 3.5883. Min Act: -0.0000

Data Index: 858152 (C4 (Web Text))

Max Activating Token Index: 107

Text #19

Max Range: 3.7767. Min Range: -3.7767

Max Act: 3.5985. Min Act: -0.0000

Data Index: 1347171 (C4 (Web Text))

Max Activating Token Index: 131