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

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

Neuron 2222 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: 0.3315. Min Range: -0.3315

Max Act: 0.3315. Min Act: -0.0000

Data Index: 917015 (C4 (Web Text))

Max Activating Token Index: 185

Text #1

Max Range: 0.3315. Min Range: -0.3315

Max Act: 0.2935. Min Act: -0.0000

Data Index: 621151 (C4 (Web Text))

Max Activating Token Index: 512

Text #2

Max Range: 0.3315. Min Range: -0.3315

Max Act: 0.2836. Min Act: -0.0000

Data Index: 322140 (C4 (Web Text))

Max Activating Token Index: 538

Text #3

Max Range: 0.3315. Min Range: -0.3315

Max Act: 0.2835. Min Act: -0.0001

Data Index: 644345 (C4 (Web Text))

Max Activating Token Index: 887

Text #4

Max Range: 0.3315. Min Range: -0.3315

Max Act: 0.3091. Min Act: -0.0000

Data Index: 937254 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 0.3315. Min Range: -0.3315

Max Act: 0.2766. Min Act: -0.0000

Data Index: 99179 (C4 (Web Text))

Max Activating Token Index: 947

Text #6

Max Range: 0.3315. Min Range: -0.3315

Max Act: 0.2737. Min Act: -0.0000

Data Index: 1249686 (C4 (Web Text))

Max Activating Token Index: 181

Text #7

Max Range: 0.3315. Min Range: -0.3315

Max Act: 0.2889. Min Act: -0.0000

Data Index: 174349 (C4 (Web Text))

Max Activating Token Index: 131

Text #8

Max Range: 0.3315. Min Range: -0.3315

Max Act: 0.2797. Min Act: -0.0000

Data Index: 83292 (C4 (Web Text))

Max Activating Token Index: 238

Text #9

Max Range: 0.3315. Min Range: -0.3315

Max Act: 0.2760. Min Act: -0.0000

Data Index: 949412 (C4 (Web Text))

Max Activating Token Index: 693

Text #10

Max Range: 0.3315. Min Range: -0.3315

Max Act: 0.2775. Min Act: -0.0000

Data Index: 775847 (C4 (Web Text))

Max Activating Token Index: 76

Text #11

Max Range: 0.3315. Min Range: -0.3315

Max Act: 0.2525. Min Act: -0.0000

Data Index: 51639 (C4 (Web Text))

Max Activating Token Index: 270

Text #12

Max Range: 0.3315. Min Range: -0.3315

Max Act: 0.2577. Min Act: -0.0000

Data Index: 1269080 (C4 (Web Text))

Max Activating Token Index: 750

Text #13

Max Range: 0.3315. Min Range: -0.3315

Max Act: 0.2658. Min Act: -0.0001

Data Index: 180661 (C4 (Web Text))

Max Activating Token Index: 559

Text #14

Max Range: 0.3315. Min Range: -0.3315

Max Act: 0.2535. Min Act: -0.0000

Data Index: 432725 (C4 (Web Text))

Max Activating Token Index: 255

Text #15

Max Range: 0.3315. Min Range: -0.3315

Max Act: 0.2518. Min Act: -0.0000

Data Index: 1058010 (C4 (Web Text))

Max Activating Token Index: 655

Text #16

Max Range: 0.3315. Min Range: -0.3315

Max Act: 0.2423. Min Act: -0.0000

Data Index: 140975 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 0.3315. Min Range: -0.3315

Max Act: 0.2315. Min Act: -0.0001

Data Index: 949777 (C4 (Web Text))

Max Activating Token Index: 1022

Text #18

Max Range: 0.3315. Min Range: -0.3315

Max Act: 0.2300. Min Act: -0.0000

Data Index: 1014527 (C4 (Web Text))

Max Activating Token Index: 673

Text #19

Max Range: 0.3315. Min Range: -0.3315

Max Act: 0.2358. Min Act: -0.0000

Data Index: 895968 (C4 (Web Text))

Max Activating Token Index: 369