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

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

Neuron 2456 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: 0.5464. Min Range: -0.5464

Max Act: 0.5464. Min Act: -0.0000

Data Index: 1277366 (C4 (Web Text))

Max Activating Token Index: 206

Text #1

Max Range: 0.5464. Min Range: -0.5464

Max Act: 0.4037. Min Act: -0.0000

Data Index: 844718 (C4 (Web Text))

Max Activating Token Index: 737

Text #2

Max Range: 0.5464. Min Range: -0.5464

Max Act: 0.3824. Min Act: -0.0001

Data Index: 390506 (C4 (Web Text))

Max Activating Token Index: 582

Text #3

Max Range: 0.5464. Min Range: -0.5464

Max Act: 0.3978. Min Act: -0.0001

Data Index: 680560 (C4 (Web Text))

Max Activating Token Index: 374

Text #4

Max Range: 0.5464. Min Range: -0.5464

Max Act: 0.3983. Min Act: -0.0001

Data Index: 1595672 (Python Code)

Max Activating Token Index: 636

Text #5

Max Range: 0.5464. Min Range: -0.5464

Max Act: 0.3890. Min Act: -0.0001

Data Index: 1336741 (C4 (Web Text))

Max Activating Token Index: 652

Text #6

Max Range: 0.5464. Min Range: -0.5464

Max Act: 0.3802. Min Act: -0.0001

Data Index: 166762 (C4 (Web Text))

Max Activating Token Index: 278

Text #7

Max Range: 0.5464. Min Range: -0.5464

Max Act: 0.3859. Min Act: -0.0001

Data Index: 480774 (C4 (Web Text))

Max Activating Token Index: 635

Text #8

Max Range: 0.5464. Min Range: -0.5464

Max Act: 0.3693. Min Act: -0.0001

Data Index: 597388 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 0.5464. Min Range: -0.5464

Max Act: 0.3506. Min Act: -0.0000

Data Index: 442367 (C4 (Web Text))

Max Activating Token Index: 843

Text #10

Max Range: 0.5464. Min Range: -0.5464

Max Act: 0.3657. Min Act: -0.0001

Data Index: 336463 (C4 (Web Text))

Max Activating Token Index: 367

Text #11

Max Range: 0.5464. Min Range: -0.5464

Max Act: 0.3288. Min Act: -0.0000

Data Index: 128376 (C4 (Web Text))

Max Activating Token Index: 161

Text #12

Max Range: 0.5464. Min Range: -0.5464

Max Act: 0.3385. Min Act: -0.0001

Data Index: 1524906 (Python Code)

Max Activating Token Index: 999

Text #13

Max Range: 0.5464. Min Range: -0.5464

Max Act: 0.3310. Min Act: -0.0000

Data Index: 1315086 (C4 (Web Text))

Max Activating Token Index: 907

Text #14

Max Range: 0.5464. Min Range: -0.5464

Max Act: 0.3606. Min Act: -0.0001

Data Index: 1582012 (Python Code)

Max Activating Token Index: 591

Text #15

Max Range: 0.5464. Min Range: -0.5464

Max Act: 0.3146. Min Act: -0.0000

Data Index: 1466021 (Python Code)

Max Activating Token Index: 633

Text #16

Max Range: 0.5464. Min Range: -0.5464

Max Act: 0.3165. Min Act: -0.0001

Data Index: 841687 (C4 (Web Text))

Max Activating Token Index: 966

Text #17

Max Range: 0.5464. Min Range: -0.5464

Max Act: 0.3061. Min Act: -0.0000

Data Index: 1520098 (Python Code)

Max Activating Token Index: 565

Text #18

Max Range: 0.5464. Min Range: -0.5464

Max Act: 0.3174. Min Act: -0.0001

Data Index: 1629335 (Python Code)

Max Activating Token Index: 589

Text #19

Max Range: 0.5464. Min Range: -0.5464

Max Act: 0.2946. Min Act: -0.0001

Data Index: 1406881 (Python Code)

Max Activating Token Index: 1001