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

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

Neuron 1243 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.4847. Min Act: -0.0001

Data Index: 610857 (C4 (Web Text))

Max Activating Token Index: 445

Text #1

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.4496. Min Act: -0.0001

Data Index: 47398 (C4 (Web Text))

Max Activating Token Index: 468

Text #2

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.4116. Min Act: -0.0001

Data Index: 582680 (C4 (Web Text))

Max Activating Token Index: 218

Text #3

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.4140. Min Act: -0.0001

Data Index: 722126 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3897. Min Act: -0.0001

Data Index: 472052 (C4 (Web Text))

Max Activating Token Index: 186

Text #5

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3907. Min Act: -0.0001

Data Index: 1107100 (C4 (Web Text))

Max Activating Token Index: 294

Text #6

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3856. Min Act: -0.0001

Data Index: 1334656 (C4 (Web Text))

Max Activating Token Index: 574

Text #7

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3700. Min Act: -0.0001

Data Index: 1223112 (C4 (Web Text))

Max Activating Token Index: 965

Text #8

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3934. Min Act: -0.0001

Data Index: 466158 (C4 (Web Text))

Max Activating Token Index: 802

Text #9

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3734. Min Act: -0.0001

Data Index: 1088914 (C4 (Web Text))

Max Activating Token Index: 233

Text #10

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3874. Min Act: -0.0001

Data Index: 1310348 (C4 (Web Text))

Max Activating Token Index: 422

Text #11

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3702. Min Act: -0.0001

Data Index: 838131 (C4 (Web Text))

Max Activating Token Index: 956

Text #12

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3703. Min Act: -0.0001

Data Index: 684797 (C4 (Web Text))

Max Activating Token Index: 427

Text #13

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3692. Min Act: -0.0001

Data Index: 726547 (C4 (Web Text))

Max Activating Token Index: 774

Text #14

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3553. Min Act: -0.0001

Data Index: 1887 (C4 (Web Text))

Max Activating Token Index: 999

Text #15

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3820. Min Act: -0.0001

Data Index: 1136031 (C4 (Web Text))

Max Activating Token Index: 134

Text #16

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3584. Min Act: -0.0001

Data Index: 100395 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3416. Min Act: -0.0001

Data Index: 649055 (C4 (Web Text))

Max Activating Token Index: 698

Text #18

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3472. Min Act: -0.0001

Data Index: 331758 (C4 (Web Text))

Max Activating Token Index: 915

Text #19

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3426. Min Act: -0.0001

Data Index: 1277754 (C4 (Web Text))

Max Activating Token Index: 898