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

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

Neuron 3889 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: 0.3584. Min Range: -0.3584

Max Act: 0.3584. Min Act: 0.0001

Data Index: 511244 (C4 (Web Text))

Max Activating Token Index: 538

Text #1

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.3294. Min Act: -0.0000

Data Index: 262522 (C4 (Web Text))

Max Activating Token Index: 1020

Text #2

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.3138. Min Act: -0.0000

Data Index: 792560 (C4 (Web Text))

Max Activating Token Index: 668

Text #3

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.3160. Min Act: -0.0000

Data Index: 110669 (C4 (Web Text))

Max Activating Token Index: 219

Text #4

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.3028. Min Act: -0.0001

Data Index: 1204752 (C4 (Web Text))

Max Activating Token Index: 60

Text #5

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.2972. Min Act: -0.0000

Data Index: 820807 (C4 (Web Text))

Max Activating Token Index: 927

Text #6

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.2885. Min Act: -0.0000

Data Index: 538281 (C4 (Web Text))

Max Activating Token Index: 236

Text #7

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.2730. Min Act: -0.0001

Data Index: 251298 (C4 (Web Text))

Max Activating Token Index: 226

Text #8

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.2818. Min Act: -0.0000

Data Index: 834784 (C4 (Web Text))

Max Activating Token Index: 453

Text #9

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.2708. Min Act: -0.0000

Data Index: 637948 (C4 (Web Text))

Max Activating Token Index: 276

Text #10

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.2792. Min Act: -0.0000

Data Index: 1268100 (C4 (Web Text))

Max Activating Token Index: 122

Text #11

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.2737. Min Act: -0.0001

Data Index: 944739 (C4 (Web Text))

Max Activating Token Index: 215

Text #12

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.2694. Min Act: -0.0001

Data Index: 872894 (C4 (Web Text))

Max Activating Token Index: 119

Text #13

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.2597. Min Act: -0.0001

Data Index: 253308 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.2495. Min Act: -0.0000

Data Index: 904776 (C4 (Web Text))

Max Activating Token Index: 218

Text #15

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.2480. Min Act: -0.0000

Data Index: 530114 (C4 (Web Text))

Max Activating Token Index: 780

Text #16

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.2457. Min Act: -0.0000

Data Index: 38500 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.2686. Min Act: -0.0000

Data Index: 515479 (C4 (Web Text))

Max Activating Token Index: 831

Text #18

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.2404. Min Act: -0.0000

Data Index: 312175 (C4 (Web Text))

Max Activating Token Index: 715

Text #19

Max Range: 0.3584. Min Range: -0.3584

Max Act: 0.2366. Min Act: -0.0000

Data Index: 12220 (C4 (Web Text))

Max Activating Token Index: 238