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

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

Neuron 606 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8941. Min Range: -0.8941

Max Act: 0.8941. Min Act: -0.0001

Data Index: 489718 (C4 (Web Text))

Max Activating Token Index: 548

Text #1

Max Range: 0.8941. Min Range: -0.8941

Max Act: 0.7953. Min Act: -0.0001

Data Index: 373877 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 0.8941. Min Range: -0.8941

Max Act: 0.7169. Min Act: -0.0001

Data Index: 543159 (C4 (Web Text))

Max Activating Token Index: 747

Text #3

Max Range: 0.8941. Min Range: -0.8941

Max Act: 0.7605. Min Act: -0.0000

Data Index: 997244 (C4 (Web Text))

Max Activating Token Index: 603

Text #4

Max Range: 0.8941. Min Range: -0.8941

Max Act: 0.7845. Min Act: -0.0001

Data Index: 492261 (C4 (Web Text))

Max Activating Token Index: 928

Text #5

Max Range: 0.8941. Min Range: -0.8941

Max Act: 0.7749. Min Act: -0.0001

Data Index: 1164047 (C4 (Web Text))

Max Activating Token Index: 807

Text #6

Max Range: 0.8941. Min Range: -0.8941

Max Act: 0.8002. Min Act: -0.0000

Data Index: 830575 (C4 (Web Text))

Max Activating Token Index: 514

Text #7

Max Range: 0.8941. Min Range: -0.8941

Max Act: 0.7707. Min Act: -0.0001

Data Index: 1291027 (C4 (Web Text))

Max Activating Token Index: 667

Text #8

Max Range: 0.8941. Min Range: -0.8941

Max Act: 0.7235. Min Act: -0.0000

Data Index: 500667 (C4 (Web Text))

Max Activating Token Index: 313

Text #9

Max Range: 0.8941. Min Range: -0.8941

Max Act: 0.7811. Min Act: -0.0001

Data Index: 962070 (C4 (Web Text))

Max Activating Token Index: 899

Text #10

Max Range: 0.8941. Min Range: -0.8941

Max Act: 0.7462. Min Act: -0.0001

Data Index: 1041104 (C4 (Web Text))

Max Activating Token Index: 646

Text #11

Max Range: 0.8941. Min Range: -0.8941

Max Act: 0.7253. Min Act: -0.0001

Data Index: 263866 (C4 (Web Text))

Max Activating Token Index: 859

Text #12

Max Range: 0.8941. Min Range: -0.8941

Max Act: 0.7376. Min Act: -0.0001

Data Index: 310272 (C4 (Web Text))

Max Activating Token Index: 435

Text #13

Max Range: 0.8941. Min Range: -0.8941

Max Act: 0.8022. Min Act: -0.0001

Data Index: 417689 (C4 (Web Text))

Max Activating Token Index: 852

Text #14

Max Range: 0.8941. Min Range: -0.8941

Max Act: 0.7373. Min Act: -0.0001

Data Index: 87824 (C4 (Web Text))

Max Activating Token Index: 285

Text #15

Max Range: 0.8941. Min Range: -0.8941

Max Act: 0.7825. Min Act: -0.0001

Data Index: 694950 (C4 (Web Text))

Max Activating Token Index: 953

Text #16

Max Range: 0.8941. Min Range: -0.8941

Max Act: 0.7118. Min Act: -0.0001

Data Index: 38817 (C4 (Web Text))

Max Activating Token Index: 221

Text #17

Max Range: 0.8941. Min Range: -0.8941

Max Act: 0.7111. Min Act: -0.0001

Data Index: 1323718 (C4 (Web Text))

Max Activating Token Index: 398

Text #18

Max Range: 0.8941. Min Range: -0.8941

Max Act: 0.7449. Min Act: -0.0000

Data Index: 162634 (C4 (Web Text))

Max Activating Token Index: 855

Text #19

Max Range: 0.8941. Min Range: -0.8941

Max Act: 0.7502. Min Act: -0.0001

Data Index: 18691 (C4 (Web Text))

Max Activating Token Index: 297