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

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

Neuron 615 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0179. Min Range: -1.0179

Max Act: 1.0179. Min Act: -0.0001

Data Index: 786401 (C4 (Web Text))

Max Activating Token Index: 86

Text #1

Max Range: 1.0179. Min Range: -1.0179

Max Act: 0.9855. Min Act: -0.0001

Data Index: 313380 (C4 (Web Text))

Max Activating Token Index: 667

Text #2

Max Range: 1.0179. Min Range: -1.0179

Max Act: 0.9606. Min Act: -0.0001

Data Index: 88074 (C4 (Web Text))

Max Activating Token Index: 321

Text #3

Max Range: 1.0179. Min Range: -1.0179

Max Act: 0.8806. Min Act: -0.0001

Data Index: 621142 (C4 (Web Text))

Max Activating Token Index: 92

Text #4

Max Range: 1.0179. Min Range: -1.0179

Max Act: 0.8934. Min Act: -0.0001

Data Index: 1283450 (C4 (Web Text))

Max Activating Token Index: 195

Text #5

Max Range: 1.0179. Min Range: -1.0179

Max Act: 0.8701. Min Act: -0.0001

Data Index: 1181979 (C4 (Web Text))

Max Activating Token Index: 220

Text #6

Max Range: 1.0179. Min Range: -1.0179

Max Act: 0.8621. Min Act: -0.0001

Data Index: 380679 (C4 (Web Text))

Max Activating Token Index: 483

Text #7

Max Range: 1.0179. Min Range: -1.0179

Max Act: 0.8542. Min Act: -0.0001

Data Index: 836049 (C4 (Web Text))

Max Activating Token Index: 148

Text #8

Max Range: 1.0179. Min Range: -1.0179

Max Act: 0.7969. Min Act: -0.0001

Data Index: 1100162 (C4 (Web Text))

Max Activating Token Index: 1006

Text #9

Max Range: 1.0179. Min Range: -1.0179

Max Act: 0.8416. Min Act: -0.0001

Data Index: 414481 (C4 (Web Text))

Max Activating Token Index: 352

Text #10

Max Range: 1.0179. Min Range: -1.0179

Max Act: 0.8344. Min Act: -0.0001

Data Index: 1184896 (C4 (Web Text))

Max Activating Token Index: 922

Text #11

Max Range: 1.0179. Min Range: -1.0179

Max Act: 0.8041. Min Act: -0.0001

Data Index: 383369 (C4 (Web Text))

Max Activating Token Index: 1011

Text #12

Max Range: 1.0179. Min Range: -1.0179

Max Act: 0.8548. Min Act: -0.0001

Data Index: 284480 (C4 (Web Text))

Max Activating Token Index: 842

Text #13

Max Range: 1.0179. Min Range: -1.0179

Max Act: 0.8575. Min Act: -0.0001

Data Index: 1074030 (C4 (Web Text))

Max Activating Token Index: 779

Text #14

Max Range: 1.0179. Min Range: -1.0179

Max Act: 0.8409. Min Act: -0.0001

Data Index: 317705 (C4 (Web Text))

Max Activating Token Index: 355

Text #15

Max Range: 1.0179. Min Range: -1.0179

Max Act: 0.7866. Min Act: -0.0001

Data Index: 1010756 (C4 (Web Text))

Max Activating Token Index: 837

Text #16

Max Range: 1.0179. Min Range: -1.0179

Max Act: 0.7567. Min Act: -0.0001

Data Index: 536182 (C4 (Web Text))

Max Activating Token Index: 769

Text #17

Max Range: 1.0179. Min Range: -1.0179

Max Act: 0.7641. Min Act: -0.0001

Data Index: 442335 (C4 (Web Text))

Max Activating Token Index: 137

Text #18

Max Range: 1.0179. Min Range: -1.0179

Max Act: 0.8184. Min Act: -0.0001

Data Index: 1255034 (C4 (Web Text))

Max Activating Token Index: 347

Text #19

Max Range: 1.0179. Min Range: -1.0179

Max Act: 0.8141. Min Act: -0.0001

Data Index: 230619 (C4 (Web Text))

Max Activating Token Index: 915