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

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

Neuron 680 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2075. Min Range: -2.2075

Max Act: 2.2075. Min Act: -0.0000

Data Index: 691474 (C4 (Web Text))

Max Activating Token Index: 236

Text #1

Max Range: 2.2075. Min Range: -2.2075

Max Act: 2.1115. Min Act: -0.0000

Data Index: 511820 (C4 (Web Text))

Max Activating Token Index: 589

Text #2

Max Range: 2.2075. Min Range: -2.2075

Max Act: 1.9215. Min Act: -0.0000

Data Index: 44673 (C4 (Web Text))

Max Activating Token Index: 106

Text #3

Max Range: 2.2075. Min Range: -2.2075

Max Act: 1.8057. Min Act: -0.0000

Data Index: 1311333 (C4 (Web Text))

Max Activating Token Index: 597

Text #4

Max Range: 2.2075. Min Range: -2.2075

Max Act: 1.7649. Min Act: -0.0000

Data Index: 1266724 (C4 (Web Text))

Max Activating Token Index: 786

Text #5

Max Range: 2.2075. Min Range: -2.2075

Max Act: 1.5751. Min Act: -0.0000

Data Index: 777551 (C4 (Web Text))

Max Activating Token Index: 1012

Text #6

Max Range: 2.2075. Min Range: -2.2075

Max Act: 1.6872. Min Act: -0.0000

Data Index: 955946 (C4 (Web Text))

Max Activating Token Index: 469

Text #7

Max Range: 2.2075. Min Range: -2.2075

Max Act: 1.5958. Min Act: -0.0000

Data Index: 198781 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 2.2075. Min Range: -2.2075

Max Act: 1.5634. Min Act: -0.0000

Data Index: 1024717 (C4 (Web Text))

Max Activating Token Index: 66

Text #9

Max Range: 2.2075. Min Range: -2.2075

Max Act: 1.4624. Min Act: -0.0000

Data Index: 809993 (C4 (Web Text))

Max Activating Token Index: 916

Text #10

Max Range: 2.2075. Min Range: -2.2075

Max Act: 1.5096. Min Act: -0.0000

Data Index: 815228 (C4 (Web Text))

Max Activating Token Index: 508

Text #11

Max Range: 2.2075. Min Range: -2.2075

Max Act: 1.4249. Min Act: -0.0000

Data Index: 960903 (C4 (Web Text))

Max Activating Token Index: 153

Text #12

Max Range: 2.2075. Min Range: -2.2075

Max Act: 1.4936. Min Act: -0.0000

Data Index: 124803 (C4 (Web Text))

Max Activating Token Index: 55

Text #13

Max Range: 2.2075. Min Range: -2.2075

Max Act: 1.4829. Min Act: -0.0000

Data Index: 1142993 (C4 (Web Text))

Max Activating Token Index: 131

Text #14

Max Range: 2.2075. Min Range: -2.2075

Max Act: 1.6333. Min Act: -0.0000

Data Index: 1057540 (C4 (Web Text))

Max Activating Token Index: 31

Text #15

Max Range: 2.2075. Min Range: -2.2075

Max Act: 1.3952. Min Act: -0.0000

Data Index: 1189432 (C4 (Web Text))

Max Activating Token Index: 414

Text #16

Max Range: 2.2075. Min Range: -2.2075

Max Act: 1.5060. Min Act: -0.0000

Data Index: 1057041 (C4 (Web Text))

Max Activating Token Index: 21

Text #17

Max Range: 2.2075. Min Range: -2.2075

Max Act: 1.4127. Min Act: -0.0000

Data Index: 1070608 (C4 (Web Text))

Max Activating Token Index: 372

Text #18

Max Range: 2.2075. Min Range: -2.2075

Max Act: 1.4354. Min Act: -0.0000

Data Index: 955642 (C4 (Web Text))

Max Activating Token Index: 289

Text #19

Max Range: 2.2075. Min Range: -2.2075

Max Act: 1.4714. Min Act: -0.0000

Data Index: 899246 (C4 (Web Text))

Max Activating Token Index: 513