Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 708 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0521. Min Range: -1.0521

Max Act: 1.0191. Min Act: -0.0001

Data Index: 720720 (C4 (Web Text))

Max Activating Token Index: 113

Text #1

Max Range: 1.0521. Min Range: -1.0521

Max Act: 1.0370. Min Act: -0.0001

Data Index: 1183913 (C4 (Web Text))

Max Activating Token Index: 938

Text #2

Max Range: 1.0521. Min Range: -1.0521

Max Act: 1.0067. Min Act: -0.0001

Data Index: 1009144 (C4 (Web Text))

Max Activating Token Index: 999

Text #3

Max Range: 1.0521. Min Range: -1.0521

Max Act: 0.9782. Min Act: -0.0001

Data Index: 1203093 (C4 (Web Text))

Max Activating Token Index: 179

Text #4

Max Range: 1.0521. Min Range: -1.0521

Max Act: 1.0305. Min Act: -0.0001

Data Index: 784303 (C4 (Web Text))

Max Activating Token Index: 863

Text #5

Max Range: 1.0521. Min Range: -1.0521

Max Act: 1.0223. Min Act: -0.0001

Data Index: 116860 (C4 (Web Text))

Max Activating Token Index: 95

Text #6

Max Range: 1.0521. Min Range: -1.0521

Max Act: 1.0521. Min Act: -0.0001

Data Index: 520881 (C4 (Web Text))

Max Activating Token Index: 782

Text #7

Max Range: 1.0521. Min Range: -1.0521

Max Act: 1.0143. Min Act: -0.0001

Data Index: 681933 (C4 (Web Text))

Max Activating Token Index: 236

Text #8

Max Range: 1.0521. Min Range: -1.0521

Max Act: 0.9806. Min Act: -0.0001

Data Index: 11914 (C4 (Web Text))

Max Activating Token Index: 654

Text #9

Max Range: 1.0521. Min Range: -1.0521

Max Act: 0.9391. Min Act: -0.0001

Data Index: 1192003 (C4 (Web Text))

Max Activating Token Index: 595

Text #10

Max Range: 1.0521. Min Range: -1.0521

Max Act: 0.9215. Min Act: -0.0001

Data Index: 236361 (C4 (Web Text))

Max Activating Token Index: 954

Text #11

Max Range: 1.0521. Min Range: -1.0521

Max Act: 0.8806. Min Act: -0.0001

Data Index: 302818 (C4 (Web Text))

Max Activating Token Index: 301

Text #12

Max Range: 1.0521. Min Range: -1.0521

Max Act: 0.7978. Min Act: -0.0001

Data Index: 794496 (C4 (Web Text))

Max Activating Token Index: 589

Text #13

Max Range: 1.0521. Min Range: -1.0521

Max Act: 0.7861. Min Act: -0.0001

Data Index: 307177 (C4 (Web Text))

Max Activating Token Index: 938

Text #14

Max Range: 1.0521. Min Range: -1.0521

Max Act: 0.7865. Min Act: -0.0001

Data Index: 8376 (C4 (Web Text))

Max Activating Token Index: 270

Text #15

Max Range: 1.0521. Min Range: -1.0521

Max Act: 0.8430. Min Act: -0.0001

Data Index: 893523 (C4 (Web Text))

Max Activating Token Index: 729

Text #16

Max Range: 1.0521. Min Range: -1.0521

Max Act: 0.7350. Min Act: -0.0001

Data Index: 462074 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 1.0521. Min Range: -1.0521

Max Act: 0.7124. Min Act: -0.0001

Data Index: 1127940 (C4 (Web Text))

Max Activating Token Index: 172

Text #18

Max Range: 1.0521. Min Range: -1.0521

Max Act: 0.6782. Min Act: -0.0001

Data Index: 657061 (C4 (Web Text))

Max Activating Token Index: 131

Text #19

Max Range: 1.0521. Min Range: -1.0521

Max Act: 0.6886. Min Act: -0.0001

Data Index: 1237750 (C4 (Web Text))

Max Activating Token Index: 823