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

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

Neuron 4224 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5037. Min Range: -5.5037

Max Act: 5.5037. Min Act: -0.0000

Data Index: 789657 (C4 (Web Text))

Max Activating Token Index: 1003

Text #1

Max Range: 5.5037. Min Range: -5.5037

Max Act: 4.7348. Min Act: -0.0000

Data Index: 1475710 (Python Code)

Max Activating Token Index: 238

Text #2

Max Range: 5.5037. Min Range: -5.5037

Max Act: 4.4995. Min Act: -0.0000

Data Index: 1522781 (Python Code)

Max Activating Token Index: 991

Text #3

Max Range: 5.5037. Min Range: -5.5037

Max Act: 4.2908. Min Act: -0.0000

Data Index: 1650787 (Python Code)

Max Activating Token Index: 245

Text #4

Max Range: 5.5037. Min Range: -5.5037

Max Act: 4.4007. Min Act: -0.0000

Data Index: 1555173 (Python Code)

Max Activating Token Index: 949

Text #5

Max Range: 5.5037. Min Range: -5.5037

Max Act: 4.0921. Min Act: -0.0000

Data Index: 1599720 (Python Code)

Max Activating Token Index: 236

Text #6

Max Range: 5.5037. Min Range: -5.5037

Max Act: 4.2284. Min Act: -0.0000

Data Index: 754743 (C4 (Web Text))

Max Activating Token Index: 701

Text #7

Max Range: 5.5037. Min Range: -5.5037

Max Act: 3.8122. Min Act: -0.0000

Data Index: 665548 (C4 (Web Text))

Max Activating Token Index: 232

Text #8

Max Range: 5.5037. Min Range: -5.5037

Max Act: 3.9859. Min Act: -0.0000

Data Index: 1380059 (Python Code)

Max Activating Token Index: 971

Text #9

Max Range: 5.5037. Min Range: -5.5037

Max Act: 3.8026. Min Act: -0.0000

Data Index: 344216 (C4 (Web Text))

Max Activating Token Index: 453

Text #10

Max Range: 5.5037. Min Range: -5.5037

Max Act: 3.7171. Min Act: -0.0000

Data Index: 428274 (C4 (Web Text))

Max Activating Token Index: 776

Text #11

Max Range: 5.5037. Min Range: -5.5037

Max Act: 3.8672. Min Act: -0.0000

Data Index: 968605 (C4 (Web Text))

Max Activating Token Index: 222

Text #12

Max Range: 5.5037. Min Range: -5.5037

Max Act: 3.7056. Min Act: -0.0000

Data Index: 390501 (C4 (Web Text))

Max Activating Token Index: 600

Text #13

Max Range: 5.5037. Min Range: -5.5037

Max Act: 3.6815. Min Act: -0.0000

Data Index: 266845 (C4 (Web Text))

Max Activating Token Index: 591

Text #14

Max Range: 5.5037. Min Range: -5.5037

Max Act: 3.8517. Min Act: -0.0000

Data Index: 1115043 (C4 (Web Text))

Max Activating Token Index: 304

Text #15

Max Range: 5.5037. Min Range: -5.5037

Max Act: 3.5925. Min Act: -0.0000

Data Index: 1219569 (C4 (Web Text))

Max Activating Token Index: 1015

Text #16

Max Range: 5.5037. Min Range: -5.5037

Max Act: 3.6197. Min Act: -0.0000

Data Index: 823773 (C4 (Web Text))

Max Activating Token Index: 112

Text #17

Max Range: 5.5037. Min Range: -5.5037

Max Act: 3.5897. Min Act: -0.0000

Data Index: 369896 (C4 (Web Text))

Max Activating Token Index: 525

Text #18

Max Range: 5.5037. Min Range: -5.5037

Max Act: 3.5593. Min Act: -0.0000

Data Index: 10680 (C4 (Web Text))

Max Activating Token Index: 523

Text #19

Max Range: 5.5037. Min Range: -5.5037

Max Act: 3.7168. Min Act: -0.0000

Data Index: 752261 (C4 (Web Text))

Max Activating Token Index: 575