Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1458 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7101. Min Range: -0.7101

Max Act: 0.7101. Min Act: -0.0001

Data Index: 1258381 (C4 (Web Text))

Max Activating Token Index: 595

Text #1

Max Range: 0.7101. Min Range: -0.7101

Max Act: 0.6774. Min Act: -0.0001

Data Index: 786702 (C4 (Web Text))

Max Activating Token Index: 325

Text #2

Max Range: 0.7101. Min Range: -0.7101

Max Act: 0.6690. Min Act: -0.0001

Data Index: 979199 (C4 (Web Text))

Max Activating Token Index: 922

Text #3

Max Range: 0.7101. Min Range: -0.7101

Max Act: 0.6327. Min Act: -0.0001

Data Index: 236799 (C4 (Web Text))

Max Activating Token Index: 375

Text #4

Max Range: 0.7101. Min Range: -0.7101

Max Act: 0.6492. Min Act: -0.0001

Data Index: 410590 (C4 (Web Text))

Max Activating Token Index: 129

Text #5

Max Range: 0.7101. Min Range: -0.7101

Max Act: 0.6451. Min Act: -0.0001

Data Index: 641881 (C4 (Web Text))

Max Activating Token Index: 171

Text #6

Max Range: 0.7101. Min Range: -0.7101

Max Act: 0.6263. Min Act: -0.0001

Data Index: 881094 (C4 (Web Text))

Max Activating Token Index: 572

Text #7

Max Range: 0.7101. Min Range: -0.7101

Max Act: 0.6189. Min Act: -0.0001

Data Index: 83130 (C4 (Web Text))

Max Activating Token Index: 438

Text #8

Max Range: 0.7101. Min Range: -0.7101

Max Act: 0.6054. Min Act: -0.0001

Data Index: 561923 (C4 (Web Text))

Max Activating Token Index: 846

Text #9

Max Range: 0.7101. Min Range: -0.7101

Max Act: 0.5995. Min Act: -0.0001

Data Index: 795812 (C4 (Web Text))

Max Activating Token Index: 156

Text #10

Max Range: 0.7101. Min Range: -0.7101

Max Act: 0.5844. Min Act: -0.0001

Data Index: 690566 (C4 (Web Text))

Max Activating Token Index: 898

Text #11

Max Range: 0.7101. Min Range: -0.7101

Max Act: 0.5655. Min Act: -0.0001

Data Index: 28249 (C4 (Web Text))

Max Activating Token Index: 424

Text #12

Max Range: 0.7101. Min Range: -0.7101

Max Act: 0.5731. Min Act: -0.0001

Data Index: 392092 (C4 (Web Text))

Max Activating Token Index: 196

Text #13

Max Range: 0.7101. Min Range: -0.7101

Max Act: 0.5510. Min Act: -0.0001

Data Index: 127049 (C4 (Web Text))

Max Activating Token Index: 388

Text #14

Max Range: 0.7101. Min Range: -0.7101

Max Act: 0.5474. Min Act: -0.0001

Data Index: 968602 (C4 (Web Text))

Max Activating Token Index: 276

Text #15

Max Range: 0.7101. Min Range: -0.7101

Max Act: 0.5658. Min Act: -0.0001

Data Index: 1197867 (C4 (Web Text))

Max Activating Token Index: 546

Text #16

Max Range: 0.7101. Min Range: -0.7101

Max Act: 0.5271. Min Act: -0.0001

Data Index: 717299 (C4 (Web Text))

Max Activating Token Index: 551

Text #17

Max Range: 0.7101. Min Range: -0.7101

Max Act: 0.5593. Min Act: -0.0001

Data Index: 1166201 (C4 (Web Text))

Max Activating Token Index: 881

Text #18

Max Range: 0.7101. Min Range: -0.7101

Max Act: 0.5321. Min Act: -0.0001

Data Index: 548710 (C4 (Web Text))

Max Activating Token Index: 64

Text #19

Max Range: 0.7101. Min Range: -0.7101

Max Act: 0.5517. Min Act: -0.0001

Data Index: 527918 (C4 (Web Text))

Max Activating Token Index: 499