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

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

Neuron 180 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.8146. Min Range: -8.8146

Max Act: 8.7969. Min Act: -0.0001

Data Index: 1221061 (C4 (Web Text))

Max Activating Token Index: 975

Text #1

Max Range: 8.8146. Min Range: -8.8146

Max Act: 8.6439. Min Act: -0.0001

Data Index: 291647 (C4 (Web Text))

Max Activating Token Index: 160

Text #2

Max Range: 8.8146. Min Range: -8.8146

Max Act: 8.8146. Min Act: -0.0001

Data Index: 639307 (C4 (Web Text))

Max Activating Token Index: 139

Text #3

Max Range: 8.8146. Min Range: -8.8146

Max Act: 8.3334. Min Act: -0.0001

Data Index: 928067 (C4 (Web Text))

Max Activating Token Index: 999

Text #4

Max Range: 8.8146. Min Range: -8.8146

Max Act: 8.4732. Min Act: -0.0001

Data Index: 747555 (C4 (Web Text))

Max Activating Token Index: 600

Text #5

Max Range: 8.8146. Min Range: -8.8146

Max Act: 7.9852. Min Act: -0.0001

Data Index: 806722 (C4 (Web Text))

Max Activating Token Index: 686

Text #6

Max Range: 8.8146. Min Range: -8.8146

Max Act: 7.7409. Min Act: -0.0000

Data Index: 926106 (C4 (Web Text))

Max Activating Token Index: 112

Text #7

Max Range: 8.8146. Min Range: -8.8146

Max Act: 7.6697. Min Act: -0.0000

Data Index: 1006815 (C4 (Web Text))

Max Activating Token Index: 1008

Text #8

Max Range: 8.8146. Min Range: -8.8146

Max Act: 7.2226. Min Act: -0.0000

Data Index: 1260740 (C4 (Web Text))

Max Activating Token Index: 217

Text #9

Max Range: 8.8146. Min Range: -8.8146

Max Act: 7.6540. Min Act: -0.0001

Data Index: 105113 (C4 (Web Text))

Max Activating Token Index: 141

Text #10

Max Range: 8.8146. Min Range: -8.8146

Max Act: 7.2411. Min Act: -0.0000

Data Index: 971489 (C4 (Web Text))

Max Activating Token Index: 148

Text #11

Max Range: 8.8146. Min Range: -8.8146

Max Act: 7.3751. Min Act: -0.0000

Data Index: 484206 (C4 (Web Text))

Max Activating Token Index: 21

Text #12

Max Range: 8.8146. Min Range: -8.8146

Max Act: 7.5334. Min Act: -0.0000

Data Index: 102436 (C4 (Web Text))

Max Activating Token Index: 258

Text #13

Max Range: 8.8146. Min Range: -8.8146

Max Act: 6.9112. Min Act: -0.0001

Data Index: 1211048 (C4 (Web Text))

Max Activating Token Index: 93

Text #14

Max Range: 8.8146. Min Range: -8.8146

Max Act: 7.0867. Min Act: -0.0000

Data Index: 106653 (C4 (Web Text))

Max Activating Token Index: 812

Text #15

Max Range: 8.8146. Min Range: -8.8146

Max Act: 7.2753. Min Act: -0.0000

Data Index: 1118745 (C4 (Web Text))

Max Activating Token Index: 512

Text #16

Max Range: 8.8146. Min Range: -8.8146

Max Act: 7.6035. Min Act: -0.0001

Data Index: 1344370 (C4 (Web Text))

Max Activating Token Index: 508

Text #17

Max Range: 8.8146. Min Range: -8.8146

Max Act: 7.3307. Min Act: -0.0001

Data Index: 804189 (C4 (Web Text))

Max Activating Token Index: 607

Text #18

Max Range: 8.8146. Min Range: -8.8146

Max Act: 7.2522. Min Act: -0.0000

Data Index: 130582 (C4 (Web Text))

Max Activating Token Index: 655

Text #19

Max Range: 8.8146. Min Range: -8.8146

Max Act: 7.2691. Min Act: -0.0000

Data Index: 1236954 (C4 (Web Text))

Max Activating Token Index: 172