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

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

Neuron 3439 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: 1.3105. Min Range: -1.3105

Max Act: 1.3105. Min Act: -0.0001

Data Index: 939724 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 1.3105. Min Range: -1.3105

Max Act: 1.1463. Min Act: -0.0001

Data Index: 658925 (C4 (Web Text))

Max Activating Token Index: 185

Text #2

Max Range: 1.3105. Min Range: -1.3105

Max Act: 1.0242. Min Act: -0.0001

Data Index: 492581 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 1.3105. Min Range: -1.3105

Max Act: 0.9451. Min Act: -0.0001

Data Index: 187180 (C4 (Web Text))

Max Activating Token Index: 536

Text #4

Max Range: 1.3105. Min Range: -1.3105

Max Act: 0.9015. Min Act: -0.0001

Data Index: 713393 (C4 (Web Text))

Max Activating Token Index: 746

Text #5

Max Range: 1.3105. Min Range: -1.3105

Max Act: 0.9110. Min Act: -0.0001

Data Index: 408675 (C4 (Web Text))

Max Activating Token Index: 397

Text #6

Max Range: 1.3105. Min Range: -1.3105

Max Act: 0.9525. Min Act: -0.0001

Data Index: 481668 (C4 (Web Text))

Max Activating Token Index: 753

Text #7

Max Range: 1.3105. Min Range: -1.3105

Max Act: 0.8953. Min Act: -0.0001

Data Index: 243213 (C4 (Web Text))

Max Activating Token Index: 103

Text #8

Max Range: 1.3105. Min Range: -1.3105

Max Act: 0.8972. Min Act: -0.0001

Data Index: 462929 (C4 (Web Text))

Max Activating Token Index: 183

Text #9

Max Range: 1.3105. Min Range: -1.3105

Max Act: 0.8440. Min Act: -0.0001

Data Index: 182789 (C4 (Web Text))

Max Activating Token Index: 136

Text #10

Max Range: 1.3105. Min Range: -1.3105

Max Act: 0.8682. Min Act: -0.0001

Data Index: 659832 (C4 (Web Text))

Max Activating Token Index: 840

Text #11

Max Range: 1.3105. Min Range: -1.3105

Max Act: 0.8324. Min Act: -0.0001

Data Index: 986418 (C4 (Web Text))

Max Activating Token Index: 88

Text #12

Max Range: 1.3105. Min Range: -1.3105

Max Act: 0.8620. Min Act: -0.0001

Data Index: 1160373 (C4 (Web Text))

Max Activating Token Index: 99

Text #13

Max Range: 1.3105. Min Range: -1.3105

Max Act: 0.8128. Min Act: -0.0001

Data Index: 1314535 (C4 (Web Text))

Max Activating Token Index: 141

Text #14

Max Range: 1.3105. Min Range: -1.3105

Max Act: 0.8607. Min Act: -0.0001

Data Index: 885463 (C4 (Web Text))

Max Activating Token Index: 556

Text #15

Max Range: 1.3105. Min Range: -1.3105

Max Act: 0.8533. Min Act: -0.0001

Data Index: 1188114 (C4 (Web Text))

Max Activating Token Index: 278

Text #16

Max Range: 1.3105. Min Range: -1.3105

Max Act: 0.8569. Min Act: -0.0001

Data Index: 441654 (C4 (Web Text))

Max Activating Token Index: 841

Text #17

Max Range: 1.3105. Min Range: -1.3105

Max Act: 0.7982. Min Act: -0.0001

Data Index: 144689 (C4 (Web Text))

Max Activating Token Index: 26

Text #18

Max Range: 1.3105. Min Range: -1.3105

Max Act: 0.8369. Min Act: -0.0001

Data Index: 627612 (C4 (Web Text))

Max Activating Token Index: 989

Text #19

Max Range: 1.3105. Min Range: -1.3105

Max Act: 0.7724. Min Act: -0.0001

Data Index: 699174 (C4 (Web Text))

Max Activating Token Index: 391