Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 881 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.4134. Min Act: -0.0000

Data Index: 1192133 (C4 (Web Text))

Max Activating Token Index: 989

Text #1

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.3765. Min Act: -0.0000

Data Index: 460257 (C4 (Web Text))

Max Activating Token Index: 185

Text #2

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.3191. Min Act: -0.0000

Data Index: 780724 (C4 (Web Text))

Max Activating Token Index: 971

Text #3

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.3075. Min Act: -0.0000

Data Index: 551390 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.3061. Min Act: -0.0000

Data Index: 842706 (C4 (Web Text))

Max Activating Token Index: 445

Text #5

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.2878. Min Act: -0.0000

Data Index: 1049815 (C4 (Web Text))

Max Activating Token Index: 490

Text #6

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.2760. Min Act: -0.0000

Data Index: 1043315 (C4 (Web Text))

Max Activating Token Index: 937

Text #7

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.2694. Min Act: -0.0000

Data Index: 1184073 (C4 (Web Text))

Max Activating Token Index: 310

Text #8

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.2528. Min Act: -0.0000

Data Index: 1293321 (C4 (Web Text))

Max Activating Token Index: 262

Text #9

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.2612. Min Act: -0.0000

Data Index: 615090 (C4 (Web Text))

Max Activating Token Index: 619

Text #10

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.2503. Min Act: -0.0000

Data Index: 776070 (C4 (Web Text))

Max Activating Token Index: 689

Text #11

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.2466. Min Act: -0.0000

Data Index: 978322 (C4 (Web Text))

Max Activating Token Index: 225

Text #12

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.2417. Min Act: -0.0000

Data Index: 261100 (C4 (Web Text))

Max Activating Token Index: 139

Text #13

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.2378. Min Act: -0.0000

Data Index: 1209520 (C4 (Web Text))

Max Activating Token Index: 142

Text #14

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.2329. Min Act: -0.0000

Data Index: 1302964 (C4 (Web Text))

Max Activating Token Index: 77

Text #15

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.2410. Min Act: -0.0000

Data Index: 1215718 (C4 (Web Text))

Max Activating Token Index: 407

Text #16

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.2240. Min Act: -0.0000

Data Index: 675139 (C4 (Web Text))

Max Activating Token Index: 347

Text #17

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.2388. Min Act: -0.0000

Data Index: 283391 (C4 (Web Text))

Max Activating Token Index: 386

Text #18

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.2339. Min Act: -0.0000

Data Index: 1113017 (C4 (Web Text))

Max Activating Token Index: 722

Text #19

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.2086. Min Act: -0.0000

Data Index: 392599 (C4 (Web Text))

Max Activating Token Index: 664