Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2026 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.9082. Min Range: -2.9082

Max Act: 2.9082. Min Act: -0.0000

Data Index: 1046846 (C4 (Web Text))

Max Activating Token Index: 596

Text #1

Max Range: 2.9082. Min Range: -2.9082

Max Act: 2.6329. Min Act: -0.0000

Data Index: 355666 (C4 (Web Text))

Max Activating Token Index: 137

Text #2

Max Range: 2.9082. Min Range: -2.9082

Max Act: 2.4489. Min Act: -0.0000

Data Index: 1119090 (C4 (Web Text))

Max Activating Token Index: 492

Text #3

Max Range: 2.9082. Min Range: -2.9082

Max Act: 2.4189. Min Act: -0.0000

Data Index: 866040 (C4 (Web Text))

Max Activating Token Index: 129

Text #4

Max Range: 2.9082. Min Range: -2.9082

Max Act: 2.2858. Min Act: -0.0000

Data Index: 757837 (C4 (Web Text))

Max Activating Token Index: 714

Text #5

Max Range: 2.9082. Min Range: -2.9082

Max Act: 2.4609. Min Act: -0.0000

Data Index: 508710 (C4 (Web Text))

Max Activating Token Index: 745

Text #6

Max Range: 2.9082. Min Range: -2.9082

Max Act: 2.5550. Min Act: -0.0000

Data Index: 48935 (C4 (Web Text))

Max Activating Token Index: 137

Text #7

Max Range: 2.9082. Min Range: -2.9082

Max Act: 2.2374. Min Act: -0.0000

Data Index: 1073652 (C4 (Web Text))

Max Activating Token Index: 4

Text #8

Max Range: 2.9082. Min Range: -2.9082

Max Act: 2.2124. Min Act: -0.0000

Data Index: 198132 (C4 (Web Text))

Max Activating Token Index: 1000

Text #9

Max Range: 2.9082. Min Range: -2.9082

Max Act: 2.2822. Min Act: -0.0000

Data Index: 388811 (C4 (Web Text))

Max Activating Token Index: 853

Text #10

Max Range: 2.9082. Min Range: -2.9082

Max Act: 2.1511. Min Act: -0.0000

Data Index: 112043 (C4 (Web Text))

Max Activating Token Index: 347

Text #11

Max Range: 2.9082. Min Range: -2.9082

Max Act: 2.2261. Min Act: -0.0000

Data Index: 827862 (C4 (Web Text))

Max Activating Token Index: 659

Text #12

Max Range: 2.9082. Min Range: -2.9082

Max Act: 2.2001. Min Act: -0.0000

Data Index: 8764 (C4 (Web Text))

Max Activating Token Index: 77

Text #13

Max Range: 2.9082. Min Range: -2.9082

Max Act: 2.0769. Min Act: -0.0000

Data Index: 1231836 (C4 (Web Text))

Max Activating Token Index: 564

Text #14

Max Range: 2.9082. Min Range: -2.9082

Max Act: 2.1967. Min Act: -0.0000

Data Index: 71511 (C4 (Web Text))

Max Activating Token Index: 541

Text #15

Max Range: 2.9082. Min Range: -2.9082

Max Act: 2.0727. Min Act: -0.0000

Data Index: 277777 (C4 (Web Text))

Max Activating Token Index: 786

Text #16

Max Range: 2.9082. Min Range: -2.9082

Max Act: 2.1720. Min Act: -0.0000

Data Index: 1270195 (C4 (Web Text))

Max Activating Token Index: 369

Text #17

Max Range: 2.9082. Min Range: -2.9082

Max Act: 2.1885. Min Act: -0.0000

Data Index: 818268 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 2.9082. Min Range: -2.9082

Max Act: 2.0481. Min Act: -0.0000

Data Index: 1303512 (C4 (Web Text))

Max Activating Token Index: 239

Text #19

Max Range: 2.9082. Min Range: -2.9082

Max Act: 2.1475. Min Act: -0.0000

Data Index: 669964 (C4 (Web Text))

Max Activating Token Index: 196