Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1115 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.0365. Min Range: -1.0365

Max Act: 1.0365. Min Act: -0.0003

Data Index: 923420 (C4 (Web Text))

Max Activating Token Index: 175

Text #1

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.9082. Min Act: -0.0003

Data Index: 57370 (C4 (Web Text))

Max Activating Token Index: 663

Text #2

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.8129. Min Act: -0.0003

Data Index: 489879 (C4 (Web Text))

Max Activating Token Index: 111

Text #3

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.7529. Min Act: -0.0003

Data Index: 187180 (C4 (Web Text))

Max Activating Token Index: 219

Text #4

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.7312. Min Act: -0.0003

Data Index: 1130363 (C4 (Web Text))

Max Activating Token Index: 515

Text #5

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.7603. Min Act: -0.0003

Data Index: 828644 (C4 (Web Text))

Max Activating Token Index: 630

Text #6

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.6852. Min Act: -0.0003

Data Index: 1309492 (C4 (Web Text))

Max Activating Token Index: 847

Text #7

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.7323. Min Act: -0.0003

Data Index: 1163994 (C4 (Web Text))

Max Activating Token Index: 957

Text #8

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.7098. Min Act: -0.0003

Data Index: 965728 (C4 (Web Text))

Max Activating Token Index: 974

Text #9

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.6799. Min Act: -0.0003

Data Index: 132494 (C4 (Web Text))

Max Activating Token Index: 528

Text #10

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.6605. Min Act: -0.0003

Data Index: 502809 (C4 (Web Text))

Max Activating Token Index: 167

Text #11

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.7020. Min Act: -0.0003

Data Index: 1219299 (C4 (Web Text))

Max Activating Token Index: 185

Text #12

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.7183. Min Act: -0.0003

Data Index: 779820 (C4 (Web Text))

Max Activating Token Index: 55

Text #13

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.6542. Min Act: -0.0003

Data Index: 290427 (C4 (Web Text))

Max Activating Token Index: 289

Text #14

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.6571. Min Act: -0.0003

Data Index: 1050133 (C4 (Web Text))

Max Activating Token Index: 833

Text #15

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.6868. Min Act: -0.0003

Data Index: 1002592 (C4 (Web Text))

Max Activating Token Index: 403

Text #16

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.6842. Min Act: -0.0003

Data Index: 355840 (C4 (Web Text))

Max Activating Token Index: 934

Text #17

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.6802. Min Act: -0.0003

Data Index: 1047793 (C4 (Web Text))

Max Activating Token Index: 111

Text #18

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.6405. Min Act: -0.0003

Data Index: 415427 (C4 (Web Text))

Max Activating Token Index: 880

Text #19

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.6808. Min Act: -0.0003

Data Index: 943638 (C4 (Web Text))

Max Activating Token Index: 128