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

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

Neuron 3624 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: 0.3782. Min Range: -0.3782

Max Act: 0.3782. Min Act: -0.0000

Data Index: 930470 (C4 (Web Text))

Max Activating Token Index: 323

Text #1

Max Range: 0.3782. Min Range: -0.3782

Max Act: 0.3544. Min Act: -0.0000

Data Index: 85611 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 0.3782. Min Range: -0.3782

Max Act: 0.3274. Min Act: -0.0000

Data Index: 277143 (C4 (Web Text))

Max Activating Token Index: 808

Text #3

Max Range: 0.3782. Min Range: -0.3782

Max Act: 0.3596. Min Act: -0.0000

Data Index: 1214502 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 0.3782. Min Range: -0.3782

Max Act: 0.3405. Min Act: -0.0000

Data Index: 994840 (C4 (Web Text))

Max Activating Token Index: 810

Text #5

Max Range: 0.3782. Min Range: -0.3782

Max Act: 0.3015. Min Act: -0.0000

Data Index: 123813 (C4 (Web Text))

Max Activating Token Index: 220

Text #6

Max Range: 0.3782. Min Range: -0.3782

Max Act: 0.3192. Min Act: -0.0000

Data Index: 184976 (C4 (Web Text))

Max Activating Token Index: 589

Text #7

Max Range: 0.3782. Min Range: -0.3782

Max Act: 0.3285. Min Act: -0.0000

Data Index: 976867 (C4 (Web Text))

Max Activating Token Index: 987

Text #8

Max Range: 0.3782. Min Range: -0.3782

Max Act: 0.3173. Min Act: -0.0000

Data Index: 1213403 (C4 (Web Text))

Max Activating Token Index: 217

Text #9

Max Range: 0.3782. Min Range: -0.3782

Max Act: 0.3145. Min Act: -0.0000

Data Index: 269169 (C4 (Web Text))

Max Activating Token Index: 340

Text #10

Max Range: 0.3782. Min Range: -0.3782

Max Act: 0.3133. Min Act: -0.0000

Data Index: 1215113 (C4 (Web Text))

Max Activating Token Index: 1011

Text #11

Max Range: 0.3782. Min Range: -0.3782

Max Act: 0.3285. Min Act: -0.0000

Data Index: 182201 (C4 (Web Text))

Max Activating Token Index: 623

Text #12

Max Range: 0.3782. Min Range: -0.3782

Max Act: 0.3532. Min Act: -0.0000

Data Index: 1320686 (C4 (Web Text))

Max Activating Token Index: 250

Text #13

Max Range: 0.3782. Min Range: -0.3782

Max Act: 0.3129. Min Act: -0.0000

Data Index: 212747 (C4 (Web Text))

Max Activating Token Index: 813

Text #14

Max Range: 0.3782. Min Range: -0.3782

Max Act: 0.3134. Min Act: -0.0000

Data Index: 1067492 (C4 (Web Text))

Max Activating Token Index: 270

Text #15

Max Range: 0.3782. Min Range: -0.3782

Max Act: 0.2922. Min Act: -0.0000

Data Index: 134584 (C4 (Web Text))

Max Activating Token Index: 767

Text #16

Max Range: 0.3782. Min Range: -0.3782

Max Act: 0.2978. Min Act: -0.0000

Data Index: 1120418 (C4 (Web Text))

Max Activating Token Index: 939

Text #17

Max Range: 0.3782. Min Range: -0.3782

Max Act: 0.3086. Min Act: -0.0000

Data Index: 1233748 (C4 (Web Text))

Max Activating Token Index: 718

Text #18

Max Range: 0.3782. Min Range: -0.3782

Max Act: 0.3208. Min Act: -0.0000

Data Index: 1191873 (C4 (Web Text))

Max Activating Token Index: 571

Text #19

Max Range: 0.3782. Min Range: -0.3782

Max Act: 0.2991. Min Act: -0.0000

Data Index: 525467 (C4 (Web Text))

Max Activating Token Index: 1017