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

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

Neuron 755 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8268. Min Range: -0.8268

Max Act: 0.8268. Min Act: -0.0001

Data Index: 600449 (C4 (Web Text))

Max Activating Token Index: 596

Text #1

Max Range: 0.8268. Min Range: -0.8268

Max Act: 0.7020. Min Act: -0.0001

Data Index: 541549 (C4 (Web Text))

Max Activating Token Index: 97

Text #2

Max Range: 0.8268. Min Range: -0.8268

Max Act: 0.7248. Min Act: -0.0001

Data Index: 538634 (C4 (Web Text))

Max Activating Token Index: 787

Text #3

Max Range: 0.8268. Min Range: -0.8268

Max Act: 0.7092. Min Act: -0.0001

Data Index: 672707 (C4 (Web Text))

Max Activating Token Index: 147

Text #4

Max Range: 0.8268. Min Range: -0.8268

Max Act: 0.8143. Min Act: -0.0001

Data Index: 350636 (C4 (Web Text))

Max Activating Token Index: 1011

Text #5

Max Range: 0.8268. Min Range: -0.8268

Max Act: 0.7003. Min Act: -0.0001

Data Index: 367047 (C4 (Web Text))

Max Activating Token Index: 1006

Text #6

Max Range: 0.8268. Min Range: -0.8268

Max Act: 0.7316. Min Act: -0.0001

Data Index: 735024 (C4 (Web Text))

Max Activating Token Index: 829

Text #7

Max Range: 0.8268. Min Range: -0.8268

Max Act: 0.7077. Min Act: -0.0001

Data Index: 917447 (C4 (Web Text))

Max Activating Token Index: 657

Text #8

Max Range: 0.8268. Min Range: -0.8268

Max Act: 0.7216. Min Act: -0.0001

Data Index: 37505 (C4 (Web Text))

Max Activating Token Index: 127

Text #9

Max Range: 0.8268. Min Range: -0.8268

Max Act: 0.6998. Min Act: -0.0001

Data Index: 317639 (C4 (Web Text))

Max Activating Token Index: 705

Text #10

Max Range: 0.8268. Min Range: -0.8268

Max Act: 0.5820. Min Act: -0.0001

Data Index: 1019748 (C4 (Web Text))

Max Activating Token Index: 660

Text #11

Max Range: 0.8268. Min Range: -0.8268

Max Act: 0.6464. Min Act: -0.0001

Data Index: 1135151 (C4 (Web Text))

Max Activating Token Index: 679

Text #12

Max Range: 0.8268. Min Range: -0.8268

Max Act: 0.6567. Min Act: -0.0001

Data Index: 1265727 (C4 (Web Text))

Max Activating Token Index: 936

Text #13

Max Range: 0.8268. Min Range: -0.8268

Max Act: 0.6529. Min Act: -0.0001

Data Index: 1185601 (C4 (Web Text))

Max Activating Token Index: 390

Text #14

Max Range: 0.8268. Min Range: -0.8268

Max Act: 0.6508. Min Act: -0.0001

Data Index: 822509 (C4 (Web Text))

Max Activating Token Index: 374

Text #15

Max Range: 0.8268. Min Range: -0.8268

Max Act: 0.6366. Min Act: -0.0001

Data Index: 804084 (C4 (Web Text))

Max Activating Token Index: 131

Text #16

Max Range: 0.8268. Min Range: -0.8268

Max Act: 0.6893. Min Act: -0.0001

Data Index: 950165 (C4 (Web Text))

Max Activating Token Index: 947

Text #17

Max Range: 0.8268. Min Range: -0.8268

Max Act: 0.4953. Min Act: -0.0001

Data Index: 1288116 (C4 (Web Text))

Max Activating Token Index: 103

Text #18

Max Range: 0.8268. Min Range: -0.8268

Max Act: 0.6772. Min Act: -0.0001

Data Index: 1073058 (C4 (Web Text))

Max Activating Token Index: 904

Text #19

Max Range: 0.8268. Min Range: -0.8268

Max Act: 0.6390. Min Act: -0.0001

Data Index: 451225 (C4 (Web Text))

Max Activating Token Index: 802