Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2301 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7539. Min Range: -0.7539

Max Act: 0.7539. Min Act: -0.0000

Data Index: 179091 (C4 (Web Text))

Max Activating Token Index: 936

Text #1

Max Range: 0.7539. Min Range: -0.7539

Max Act: 0.6066. Min Act: -0.0000

Data Index: 273044 (C4 (Web Text))

Max Activating Token Index: 239

Text #2

Max Range: 0.7539. Min Range: -0.7539

Max Act: 0.6375. Min Act: -0.0000

Data Index: 865749 (C4 (Web Text))

Max Activating Token Index: 558

Text #3

Max Range: 0.7539. Min Range: -0.7539

Max Act: 0.5957. Min Act: -0.0000

Data Index: 1352717 (C4 (Web Text))

Max Activating Token Index: 603

Text #4

Max Range: 0.7539. Min Range: -0.7539

Max Act: 0.5966. Min Act: -0.0000

Data Index: 407954 (C4 (Web Text))

Max Activating Token Index: 366

Text #5

Max Range: 0.7539. Min Range: -0.7539

Max Act: 0.6085. Min Act: -0.0000

Data Index: 140167 (C4 (Web Text))

Max Activating Token Index: 178

Text #6

Max Range: 0.7539. Min Range: -0.7539

Max Act: 0.6100. Min Act: -0.0000

Data Index: 374973 (C4 (Web Text))

Max Activating Token Index: 110

Text #7

Max Range: 0.7539. Min Range: -0.7539

Max Act: 0.5900. Min Act: -0.0000

Data Index: 761520 (C4 (Web Text))

Max Activating Token Index: 974

Text #8

Max Range: 0.7539. Min Range: -0.7539

Max Act: 0.5823. Min Act: -0.0000

Data Index: 82675 (C4 (Web Text))

Max Activating Token Index: 608

Text #9

Max Range: 0.7539. Min Range: -0.7539

Max Act: 0.5821. Min Act: -0.0000

Data Index: 1254511 (C4 (Web Text))

Max Activating Token Index: 249

Text #10

Max Range: 0.7539. Min Range: -0.7539

Max Act: 0.5995. Min Act: -0.0000

Data Index: 577941 (C4 (Web Text))

Max Activating Token Index: 149

Text #11

Max Range: 0.7539. Min Range: -0.7539

Max Act: 0.5944. Min Act: -0.0000

Data Index: 1295387 (C4 (Web Text))

Max Activating Token Index: 586

Text #12

Max Range: 0.7539. Min Range: -0.7539

Max Act: 0.6030. Min Act: -0.0000

Data Index: 761663 (C4 (Web Text))

Max Activating Token Index: 102

Text #13

Max Range: 0.7539. Min Range: -0.7539

Max Act: 0.5981. Min Act: -0.0000

Data Index: 1060562 (C4 (Web Text))

Max Activating Token Index: 288

Text #14

Max Range: 0.7539. Min Range: -0.7539

Max Act: 0.5499. Min Act: -0.0000

Data Index: 1197435 (C4 (Web Text))

Max Activating Token Index: 250

Text #15

Max Range: 0.7539. Min Range: -0.7539

Max Act: 0.6520. Min Act: -0.0000

Data Index: 1644565 (Python Code)

Max Activating Token Index: 884

Text #16

Max Range: 0.7539. Min Range: -0.7539

Max Act: 0.5687. Min Act: -0.0000

Data Index: 790518 (C4 (Web Text))

Max Activating Token Index: 430

Text #17

Max Range: 0.7539. Min Range: -0.7539

Max Act: 0.5412. Min Act: -0.0000

Data Index: 854811 (C4 (Web Text))

Max Activating Token Index: 279

Text #18

Max Range: 0.7539. Min Range: -0.7539

Max Act: 0.5469. Min Act: -0.0000

Data Index: 117610 (C4 (Web Text))

Max Activating Token Index: 46

Text #19

Max Range: 0.7539. Min Range: -0.7539

Max Act: 0.5632. Min Act: -0.0000

Data Index: 213488 (C4 (Web Text))

Max Activating Token Index: 159