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

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

Neuron 696 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4951. Min Range: -2.4951

Max Act: 2.4951. Min Act: 0.0000

Data Index: 1027130 (C4 (Web Text))

Max Activating Token Index: 370

Text #1

Max Range: 2.4951. Min Range: -2.4951

Max Act: 2.2677. Min Act: -0.0000

Data Index: 266289 (C4 (Web Text))

Max Activating Token Index: 829

Text #2

Max Range: 2.4951. Min Range: -2.4951

Max Act: 2.2274. Min Act: -0.0000

Data Index: 233972 (C4 (Web Text))

Max Activating Token Index: 625

Text #3

Max Range: 2.4951. Min Range: -2.4951

Max Act: 1.8939. Min Act: -0.0000

Data Index: 727447 (C4 (Web Text))

Max Activating Token Index: 374

Text #4

Max Range: 2.4951. Min Range: -2.4951

Max Act: 1.7868. Min Act: -0.0000

Data Index: 1215927 (C4 (Web Text))

Max Activating Token Index: 540

Text #5

Max Range: 2.4951. Min Range: -2.4951

Max Act: 1.7225. Min Act: -0.0000

Data Index: 211108 (C4 (Web Text))

Max Activating Token Index: 195

Text #6

Max Range: 2.4951. Min Range: -2.4951

Max Act: 1.7910. Min Act: -0.0000

Data Index: 348050 (C4 (Web Text))

Max Activating Token Index: 741

Text #7

Max Range: 2.4951. Min Range: -2.4951

Max Act: 1.8838. Min Act: -0.0000

Data Index: 581850 (C4 (Web Text))

Max Activating Token Index: 147

Text #8

Max Range: 2.4951. Min Range: -2.4951

Max Act: 1.7531. Min Act: -0.0000

Data Index: 882460 (C4 (Web Text))

Max Activating Token Index: 432

Text #9

Max Range: 2.4951. Min Range: -2.4951

Max Act: 1.7188. Min Act: -0.0000

Data Index: 607783 (C4 (Web Text))

Max Activating Token Index: 236

Text #10

Max Range: 2.4951. Min Range: -2.4951

Max Act: 1.6017. Min Act: -0.0000

Data Index: 1201933 (C4 (Web Text))

Max Activating Token Index: 905

Text #11

Max Range: 2.4951. Min Range: -2.4951

Max Act: 1.6144. Min Act: -0.0000

Data Index: 47591 (C4 (Web Text))

Max Activating Token Index: 571

Text #12

Max Range: 2.4951. Min Range: -2.4951

Max Act: 1.6813. Min Act: -0.0000

Data Index: 50849 (C4 (Web Text))

Max Activating Token Index: 126

Text #13

Max Range: 2.4951. Min Range: -2.4951

Max Act: 1.6545. Min Act: -0.0000

Data Index: 1509927 (Python Code)

Max Activating Token Index: 850

Text #14

Max Range: 2.4951. Min Range: -2.4951

Max Act: 1.6369. Min Act: -0.0000

Data Index: 1167235 (C4 (Web Text))

Max Activating Token Index: 855

Text #15

Max Range: 2.4951. Min Range: -2.4951

Max Act: 1.7426. Min Act: -0.0000

Data Index: 960247 (C4 (Web Text))

Max Activating Token Index: 325

Text #16

Max Range: 2.4951. Min Range: -2.4951

Max Act: 1.5911. Min Act: -0.0000

Data Index: 1333059 (C4 (Web Text))

Max Activating Token Index: 101

Text #17

Max Range: 2.4951. Min Range: -2.4951

Max Act: 1.7356. Min Act: -0.0000

Data Index: 873590 (C4 (Web Text))

Max Activating Token Index: 241

Text #18

Max Range: 2.4951. Min Range: -2.4951

Max Act: 1.6641. Min Act: -0.0000

Data Index: 50238 (C4 (Web Text))

Max Activating Token Index: 993

Text #19

Max Range: 2.4951. Min Range: -2.4951

Max Act: 1.6130. Min Act: -0.0000

Data Index: 1078161 (C4 (Web Text))

Max Activating Token Index: 553