Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2356 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.7348. Min Range: -3.7348

Max Act: 3.7348. Min Act: -0.0001

Data Index: 393697 (C4 (Web Text))

Max Activating Token Index: 429

Text #1

Max Range: 3.7348. Min Range: -3.7348

Max Act: 3.6104. Min Act: -0.0001

Data Index: 994991 (C4 (Web Text))

Max Activating Token Index: 888

Text #2

Max Range: 3.7348. Min Range: -3.7348

Max Act: 3.4462. Min Act: -0.0001

Data Index: 525105 (C4 (Web Text))

Max Activating Token Index: 389

Text #3

Max Range: 3.7348. Min Range: -3.7348

Max Act: 3.2859. Min Act: -0.0001

Data Index: 749338 (C4 (Web Text))

Max Activating Token Index: 522

Text #4

Max Range: 3.7348. Min Range: -3.7348

Max Act: 3.2821. Min Act: -0.0001

Data Index: 631421 (C4 (Web Text))

Max Activating Token Index: 843

Text #5

Max Range: 3.7348. Min Range: -3.7348

Max Act: 3.2129. Min Act: -0.0001

Data Index: 141007 (C4 (Web Text))

Max Activating Token Index: 858

Text #6

Max Range: 3.7348. Min Range: -3.7348

Max Act: 3.1991. Min Act: -0.0001

Data Index: 563005 (C4 (Web Text))

Max Activating Token Index: 653

Text #7

Max Range: 3.7348. Min Range: -3.7348

Max Act: 3.1716. Min Act: -0.0001

Data Index: 346825 (C4 (Web Text))

Max Activating Token Index: 610

Text #8

Max Range: 3.7348. Min Range: -3.7348

Max Act: 3.0234. Min Act: -0.0001

Data Index: 1287659 (C4 (Web Text))

Max Activating Token Index: 682

Text #9

Max Range: 3.7348. Min Range: -3.7348

Max Act: 3.2356. Min Act: -0.0001

Data Index: 938158 (C4 (Web Text))

Max Activating Token Index: 589

Text #10

Max Range: 3.7348. Min Range: -3.7348

Max Act: 3.0424. Min Act: -0.0001

Data Index: 1109161 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 3.7348. Min Range: -3.7348

Max Act: 2.7101. Min Act: -0.0001

Data Index: 768661 (C4 (Web Text))

Max Activating Token Index: 557

Text #12

Max Range: 3.7348. Min Range: -3.7348

Max Act: 2.9846. Min Act: -0.0001

Data Index: 975193 (C4 (Web Text))

Max Activating Token Index: 247

Text #13

Max Range: 3.7348. Min Range: -3.7348

Max Act: 2.9108. Min Act: -0.0001

Data Index: 754969 (C4 (Web Text))

Max Activating Token Index: 317

Text #14

Max Range: 3.7348. Min Range: -3.7348

Max Act: 2.7659. Min Act: -0.0001

Data Index: 1165899 (C4 (Web Text))

Max Activating Token Index: 845

Text #15

Max Range: 3.7348. Min Range: -3.7348

Max Act: 2.8463. Min Act: -0.0001

Data Index: 378192 (C4 (Web Text))

Max Activating Token Index: 80

Text #16

Max Range: 3.7348. Min Range: -3.7348

Max Act: 2.1919. Min Act: -0.0001

Data Index: 758127 (C4 (Web Text))

Max Activating Token Index: 671

Text #17

Max Range: 3.7348. Min Range: -3.7348

Max Act: 2.7831. Min Act: -0.0001

Data Index: 1218963 (C4 (Web Text))

Max Activating Token Index: 598

Text #18

Max Range: 3.7348. Min Range: -3.7348

Max Act: 2.6381. Min Act: -0.0001

Data Index: 988915 (C4 (Web Text))

Max Activating Token Index: 455

Text #19

Max Range: 3.7348. Min Range: -3.7348

Max Act: 2.6168. Min Act: -0.0001

Data Index: 871233 (C4 (Web Text))

Max Activating Token Index: 18