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

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

Neuron 616 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.4100. Min Act: -0.0001

Data Index: 325794 (C4 (Web Text))

Max Activating Token Index: 629

Text #1

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.4140. Min Act: -0.0001

Data Index: 1123355 (C4 (Web Text))

Max Activating Token Index: 378

Text #2

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.3581. Min Act: -0.0001

Data Index: 966589 (C4 (Web Text))

Max Activating Token Index: 770

Text #3

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.3531. Min Act: -0.0000

Data Index: 57496 (C4 (Web Text))

Max Activating Token Index: 611

Text #4

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.3374. Min Act: -0.0000

Data Index: 1140836 (C4 (Web Text))

Max Activating Token Index: 304

Text #5

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.3662. Min Act: -0.0001

Data Index: 323367 (C4 (Web Text))

Max Activating Token Index: 504

Text #6

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.3360. Min Act: -0.0001

Data Index: 580357 (C4 (Web Text))

Max Activating Token Index: 575

Text #7

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.3526. Min Act: -0.0001

Data Index: 439067 (C4 (Web Text))

Max Activating Token Index: 420

Text #8

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.3213. Min Act: -0.0001

Data Index: 1145962 (C4 (Web Text))

Max Activating Token Index: 236

Text #9

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.3197. Min Act: -0.0000

Data Index: 940691 (C4 (Web Text))

Max Activating Token Index: 1000

Text #10

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.3432. Min Act: -0.0000

Data Index: 214576 (C4 (Web Text))

Max Activating Token Index: 740

Text #11

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.3735. Min Act: -0.0000

Data Index: 480719 (C4 (Web Text))

Max Activating Token Index: 945

Text #12

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.3395. Min Act: -0.0001

Data Index: 1224300 (C4 (Web Text))

Max Activating Token Index: 298

Text #13

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.3087. Min Act: -0.0001

Data Index: 1098637 (C4 (Web Text))

Max Activating Token Index: 812

Text #14

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.3434. Min Act: -0.0000

Data Index: 173064 (C4 (Web Text))

Max Activating Token Index: 934

Text #15

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.3273. Min Act: -0.0001

Data Index: 1115852 (C4 (Web Text))

Max Activating Token Index: 481

Text #16

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.3129. Min Act: -0.0001

Data Index: 1154435 (C4 (Web Text))

Max Activating Token Index: 370

Text #17

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.3043. Min Act: -0.0001

Data Index: 1224555 (C4 (Web Text))

Max Activating Token Index: 638

Text #18

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.3108. Min Act: -0.0000

Data Index: 819321 (C4 (Web Text))

Max Activating Token Index: 478

Text #19

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.3207. Min Act: -0.0001

Data Index: 1149362 (C4 (Web Text))

Max Activating Token Index: 942