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

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

Neuron 728 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: 0.8681. Min Range: -0.8681

Max Act: 0.8573. Min Act: -0.0000

Data Index: 7798 (C4 (Web Text))

Max Activating Token Index: 398

Text #1

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.8118. Min Act: -0.0000

Data Index: 974775 (C4 (Web Text))

Max Activating Token Index: 341

Text #2

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.8396. Min Act: -0.0000

Data Index: 349390 (C4 (Web Text))

Max Activating Token Index: 86

Text #3

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.8681. Min Act: -0.0001

Data Index: 772900 (C4 (Web Text))

Max Activating Token Index: 286

Text #4

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.7954. Min Act: -0.0000

Data Index: 503377 (C4 (Web Text))

Max Activating Token Index: 561

Text #5

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.7359. Min Act: -0.0000

Data Index: 1199623 (C4 (Web Text))

Max Activating Token Index: 708

Text #6

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.7441. Min Act: -0.0001

Data Index: 1310322 (C4 (Web Text))

Max Activating Token Index: 929

Text #7

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.7979. Min Act: -0.0000

Data Index: 978577 (C4 (Web Text))

Max Activating Token Index: 94

Text #8

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.7339. Min Act: -0.0000

Data Index: 238073 (C4 (Web Text))

Max Activating Token Index: 424

Text #9

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.6951. Min Act: -0.0000

Data Index: 94537 (C4 (Web Text))

Max Activating Token Index: 906

Text #10

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.7470. Min Act: -0.0001

Data Index: 196723 (C4 (Web Text))

Max Activating Token Index: 529

Text #11

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.7731. Min Act: -0.0000

Data Index: 1291909 (C4 (Web Text))

Max Activating Token Index: 117

Text #12

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.7030. Min Act: -0.0000

Data Index: 828925 (C4 (Web Text))

Max Activating Token Index: 937

Text #13

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.7022. Min Act: -0.0000

Data Index: 216551 (C4 (Web Text))

Max Activating Token Index: 538

Text #14

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.7087. Min Act: -0.0000

Data Index: 354265 (C4 (Web Text))

Max Activating Token Index: 288

Text #15

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.7099. Min Act: -0.0001

Data Index: 234812 (C4 (Web Text))

Max Activating Token Index: 458

Text #16

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.6542. Min Act: -0.0000

Data Index: 318186 (C4 (Web Text))

Max Activating Token Index: 319

Text #17

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.7208. Min Act: -0.0001

Data Index: 234467 (C4 (Web Text))

Max Activating Token Index: 845

Text #18

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.7403. Min Act: -0.0000

Data Index: 1239073 (C4 (Web Text))

Max Activating Token Index: 232

Text #19

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.7382. Min Act: -0.0001

Data Index: 2331 (C4 (Web Text))

Max Activating Token Index: 424