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

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

Neuron 3756 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.7439. Min Act: -0.0001

Data Index: 307388 (C4 (Web Text))

Max Activating Token Index: 899

Text #1

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.6261. Min Act: -0.0000

Data Index: 724221 (C4 (Web Text))

Max Activating Token Index: 856

Text #2

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5848. Min Act: -0.0000

Data Index: 869522 (C4 (Web Text))

Max Activating Token Index: 493

Text #3

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5802. Min Act: -0.0000

Data Index: 837380 (C4 (Web Text))

Max Activating Token Index: 286

Text #4

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5386. Min Act: -0.0001

Data Index: 1249854 (C4 (Web Text))

Max Activating Token Index: 458

Text #5

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.4998. Min Act: -0.0001

Data Index: 89608 (C4 (Web Text))

Max Activating Token Index: 741

Text #6

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.4814. Min Act: -0.0001

Data Index: 715598 (C4 (Web Text))

Max Activating Token Index: 583

Text #7

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5071. Min Act: -0.0000

Data Index: 1150702 (C4 (Web Text))

Max Activating Token Index: 661

Text #8

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5236. Min Act: -0.0000

Data Index: 663475 (C4 (Web Text))

Max Activating Token Index: 368

Text #9

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.4600. Min Act: -0.0000

Data Index: 459313 (C4 (Web Text))

Max Activating Token Index: 159

Text #10

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.4403. Min Act: -0.0000

Data Index: 493353 (C4 (Web Text))

Max Activating Token Index: 964

Text #11

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.4435. Min Act: -0.0001

Data Index: 798375 (C4 (Web Text))

Max Activating Token Index: 167

Text #12

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.4417. Min Act: -0.0001

Data Index: 642412 (C4 (Web Text))

Max Activating Token Index: 904

Text #13

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.4415. Min Act: -0.0000

Data Index: 313001 (C4 (Web Text))

Max Activating Token Index: 770

Text #14

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.4259. Min Act: -0.0000

Data Index: 861975 (C4 (Web Text))

Max Activating Token Index: 613

Text #15

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.4320. Min Act: -0.0001

Data Index: 1126605 (C4 (Web Text))

Max Activating Token Index: 362

Text #16

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.4166. Min Act: -0.0000

Data Index: 739878 (C4 (Web Text))

Max Activating Token Index: 81

Text #17

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.4108. Min Act: -0.0001

Data Index: 525843 (C4 (Web Text))

Max Activating Token Index: 511

Text #18

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.4378. Min Act: -0.0000

Data Index: 1084019 (C4 (Web Text))

Max Activating Token Index: 787

Text #19

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.4069. Min Act: -0.0001

Data Index: 355468 (C4 (Web Text))

Max Activating Token Index: 103