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

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

Neuron 1235 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8923. Min Range: -1.8923

Max Act: 1.8923. Min Act: -0.0001

Data Index: 1107043 (C4 (Web Text))

Max Activating Token Index: 514

Text #1

Max Range: 1.8923. Min Range: -1.8923

Max Act: 1.6526. Min Act: -0.0001

Data Index: 440007 (C4 (Web Text))

Max Activating Token Index: 115

Text #2

Max Range: 1.8923. Min Range: -1.8923

Max Act: 1.5172. Min Act: -0.0001

Data Index: 1254725 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 1.8923. Min Range: -1.8923

Max Act: 1.4927. Min Act: -0.0001

Data Index: 1314002 (C4 (Web Text))

Max Activating Token Index: 342

Text #4

Max Range: 1.8923. Min Range: -1.8923

Max Act: 1.5171. Min Act: -0.0001

Data Index: 8752 (C4 (Web Text))

Max Activating Token Index: 263

Text #5

Max Range: 1.8923. Min Range: -1.8923

Max Act: 1.3237. Min Act: -0.0001

Data Index: 402191 (C4 (Web Text))

Max Activating Token Index: 813

Text #6

Max Range: 1.8923. Min Range: -1.8923

Max Act: 1.2907. Min Act: -0.0001

Data Index: 64132 (C4 (Web Text))

Max Activating Token Index: 441

Text #7

Max Range: 1.8923. Min Range: -1.8923

Max Act: 1.3473. Min Act: -0.0000

Data Index: 965736 (C4 (Web Text))

Max Activating Token Index: 768

Text #8

Max Range: 1.8923. Min Range: -1.8923

Max Act: 1.2776. Min Act: -0.0000

Data Index: 617828 (C4 (Web Text))

Max Activating Token Index: 710

Text #9

Max Range: 1.8923. Min Range: -1.8923

Max Act: 1.2786. Min Act: -0.0001

Data Index: 750130 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 1.8923. Min Range: -1.8923

Max Act: 1.2027. Min Act: -0.0001

Data Index: 853750 (C4 (Web Text))

Max Activating Token Index: 225

Text #11

Max Range: 1.8923. Min Range: -1.8923

Max Act: 1.2131. Min Act: -0.0001

Data Index: 708560 (C4 (Web Text))

Max Activating Token Index: 659

Text #12

Max Range: 1.8923. Min Range: -1.8923

Max Act: 1.2804. Min Act: -0.0000

Data Index: 279628 (C4 (Web Text))

Max Activating Token Index: 906

Text #13

Max Range: 1.8923. Min Range: -1.8923

Max Act: 1.1893. Min Act: -0.0001

Data Index: 45897 (C4 (Web Text))

Max Activating Token Index: 648

Text #14

Max Range: 1.8923. Min Range: -1.8923

Max Act: 1.2227. Min Act: -0.0001

Data Index: 589024 (C4 (Web Text))

Max Activating Token Index: 61

Text #15

Max Range: 1.8923. Min Range: -1.8923

Max Act: 1.1552. Min Act: -0.0001

Data Index: 675709 (C4 (Web Text))

Max Activating Token Index: 429

Text #16

Max Range: 1.8923. Min Range: -1.8923

Max Act: 1.1210. Min Act: -0.0000

Data Index: 453399 (C4 (Web Text))

Max Activating Token Index: 654

Text #17

Max Range: 1.8923. Min Range: -1.8923

Max Act: 1.1150. Min Act: -0.0001

Data Index: 307119 (C4 (Web Text))

Max Activating Token Index: 575

Text #18

Max Range: 1.8923. Min Range: -1.8923

Max Act: 1.1619. Min Act: -0.0001

Data Index: 326342 (C4 (Web Text))

Max Activating Token Index: 871

Text #19

Max Range: 1.8923. Min Range: -1.8923

Max Act: 1.1850. Min Act: -0.0001

Data Index: 1297014 (C4 (Web Text))

Max Activating Token Index: 230