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

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

Neuron 2668 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3069. Min Range: -2.3069

Max Act: 2.3069. Min Act: -0.0000

Data Index: 1228811 (C4 (Web Text))

Max Activating Token Index: 54

Text #1

Max Range: 2.3069. Min Range: -2.3069

Max Act: 2.2900. Min Act: -0.0000

Data Index: 851475 (C4 (Web Text))

Max Activating Token Index: 116

Text #2

Max Range: 2.3069. Min Range: -2.3069

Max Act: 2.1954. Min Act: -0.0000

Data Index: 285014 (C4 (Web Text))

Max Activating Token Index: 844

Text #3

Max Range: 2.3069. Min Range: -2.3069

Max Act: 2.1751. Min Act: -0.0000

Data Index: 703360 (C4 (Web Text))

Max Activating Token Index: 37

Text #4

Max Range: 2.3069. Min Range: -2.3069

Max Act: 1.9883. Min Act: -0.0000

Data Index: 307725 (C4 (Web Text))

Max Activating Token Index: 304

Text #5

Max Range: 2.3069. Min Range: -2.3069

Max Act: 2.0765. Min Act: -0.0000

Data Index: 675616 (C4 (Web Text))

Max Activating Token Index: 74

Text #6

Max Range: 2.3069. Min Range: -2.3069

Max Act: 2.1504. Min Act: -0.0000

Data Index: 1104309 (C4 (Web Text))

Max Activating Token Index: 216

Text #7

Max Range: 2.3069. Min Range: -2.3069

Max Act: 1.9372. Min Act: -0.0000

Data Index: 792416 (C4 (Web Text))

Max Activating Token Index: 45

Text #8

Max Range: 2.3069. Min Range: -2.3069

Max Act: 2.0736. Min Act: -0.0000

Data Index: 1109689 (C4 (Web Text))

Max Activating Token Index: 198

Text #9

Max Range: 2.3069. Min Range: -2.3069

Max Act: 1.9633. Min Act: -0.0000

Data Index: 1226308 (C4 (Web Text))

Max Activating Token Index: 937

Text #10

Max Range: 2.3069. Min Range: -2.3069

Max Act: 2.0948. Min Act: -0.0000

Data Index: 973303 (C4 (Web Text))

Max Activating Token Index: 469

Text #11

Max Range: 2.3069. Min Range: -2.3069

Max Act: 2.0585. Min Act: -0.0000

Data Index: 668820 (C4 (Web Text))

Max Activating Token Index: 350

Text #12

Max Range: 2.3069. Min Range: -2.3069

Max Act: 1.7800. Min Act: -0.0000

Data Index: 584774 (C4 (Web Text))

Max Activating Token Index: 764

Text #13

Max Range: 2.3069. Min Range: -2.3069

Max Act: 1.9437. Min Act: -0.0000

Data Index: 1052616 (C4 (Web Text))

Max Activating Token Index: 161

Text #14

Max Range: 2.3069. Min Range: -2.3069

Max Act: 1.9264. Min Act: -0.0000

Data Index: 1152078 (C4 (Web Text))

Max Activating Token Index: 36

Text #15

Max Range: 2.3069. Min Range: -2.3069

Max Act: 1.8998. Min Act: -0.0000

Data Index: 90138 (C4 (Web Text))

Max Activating Token Index: 525

Text #16

Max Range: 2.3069. Min Range: -2.3069

Max Act: 1.8940. Min Act: -0.0000

Data Index: 412467 (C4 (Web Text))

Max Activating Token Index: 501

Text #17

Max Range: 2.3069. Min Range: -2.3069

Max Act: 1.8655. Min Act: -0.0000

Data Index: 3043 (C4 (Web Text))

Max Activating Token Index: 245

Text #18

Max Range: 2.3069. Min Range: -2.3069

Max Act: 1.9655. Min Act: -0.0000

Data Index: 1212555 (C4 (Web Text))

Max Activating Token Index: 964

Text #19

Max Range: 2.3069. Min Range: -2.3069

Max Act: 1.9021. Min Act: -0.0000

Data Index: 567188 (C4 (Web Text))

Max Activating Token Index: 967