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

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

Neuron 4401 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.8935. Min Range: -1.8935

Max Act: 1.8935. Min Act: -0.0001

Data Index: 275648 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 1.8935. Min Range: -1.8935

Max Act: 1.6333. Min Act: -0.0001

Data Index: 503809 (C4 (Web Text))

Max Activating Token Index: 788

Text #2

Max Range: 1.8935. Min Range: -1.8935

Max Act: 1.6173. Min Act: -0.0001

Data Index: 123474 (C4 (Web Text))

Max Activating Token Index: 1013

Text #3

Max Range: 1.8935. Min Range: -1.8935

Max Act: 1.6459. Min Act: -0.0001

Data Index: 565497 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 1.8935. Min Range: -1.8935

Max Act: 1.5699. Min Act: -0.0000

Data Index: 1223578 (C4 (Web Text))

Max Activating Token Index: 130

Text #5

Max Range: 1.8935. Min Range: -1.8935

Max Act: 1.6197. Min Act: -0.0001

Data Index: 1277735 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 1.8935. Min Range: -1.8935

Max Act: 1.5788. Min Act: -0.0001

Data Index: 727959 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 1.8935. Min Range: -1.8935

Max Act: 1.5199. Min Act: -0.0001

Data Index: 805814 (C4 (Web Text))

Max Activating Token Index: 415

Text #8

Max Range: 1.8935. Min Range: -1.8935

Max Act: 1.5575. Min Act: -0.0001

Data Index: 236958 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 1.8935. Min Range: -1.8935

Max Act: 1.4974. Min Act: -0.0001

Data Index: 657352 (C4 (Web Text))

Max Activating Token Index: 115

Text #10

Max Range: 1.8935. Min Range: -1.8935

Max Act: 1.4509. Min Act: -0.0001

Data Index: 1260764 (C4 (Web Text))

Max Activating Token Index: 259

Text #11

Max Range: 1.8935. Min Range: -1.8935

Max Act: 1.5235. Min Act: -0.0001

Data Index: 457303 (C4 (Web Text))

Max Activating Token Index: 176

Text #12

Max Range: 1.8935. Min Range: -1.8935

Max Act: 1.5217. Min Act: -0.0001

Data Index: 17558 (C4 (Web Text))

Max Activating Token Index: 156

Text #13

Max Range: 1.8935. Min Range: -1.8935

Max Act: 1.5070. Min Act: -0.0000

Data Index: 1223042 (C4 (Web Text))

Max Activating Token Index: 1006

Text #14

Max Range: 1.8935. Min Range: -1.8935

Max Act: 1.4983. Min Act: -0.0001

Data Index: 51267 (C4 (Web Text))

Max Activating Token Index: 103

Text #15

Max Range: 1.8935. Min Range: -1.8935

Max Act: 1.5156. Min Act: -0.0001

Data Index: 316602 (C4 (Web Text))

Max Activating Token Index: 117

Text #16

Max Range: 1.8935. Min Range: -1.8935

Max Act: 1.4680. Min Act: -0.0001

Data Index: 378565 (C4 (Web Text))

Max Activating Token Index: 389

Text #17

Max Range: 1.8935. Min Range: -1.8935

Max Act: 1.3964. Min Act: -0.0001

Data Index: 205352 (C4 (Web Text))

Max Activating Token Index: 887

Text #18

Max Range: 1.8935. Min Range: -1.8935

Max Act: 1.4447. Min Act: -0.0000

Data Index: 356094 (C4 (Web Text))

Max Activating Token Index: 158

Text #19

Max Range: 1.8935. Min Range: -1.8935

Max Act: 1.3788. Min Act: -0.0001

Data Index: 468945 (C4 (Web Text))

Max Activating Token Index: 821