Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 713 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.4913. Min Act: -0.0001

Data Index: 360119 (C4 (Web Text))

Max Activating Token Index: 886

Text #1

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.4525. Min Act: -0.0001

Data Index: 394377 (C4 (Web Text))

Max Activating Token Index: 776

Text #2

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.4507. Min Act: -0.0001

Data Index: 931635 (C4 (Web Text))

Max Activating Token Index: 857

Text #3

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.4626. Min Act: -0.0001

Data Index: 893438 (C4 (Web Text))

Max Activating Token Index: 835

Text #4

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.4437. Min Act: -0.0001

Data Index: 126036 (C4 (Web Text))

Max Activating Token Index: 772

Text #5

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.4514. Min Act: -0.0001

Data Index: 228026 (C4 (Web Text))

Max Activating Token Index: 394

Text #6

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.4479. Min Act: -0.0001

Data Index: 919188 (C4 (Web Text))

Max Activating Token Index: 686

Text #7

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.4477. Min Act: -0.0001

Data Index: 632046 (C4 (Web Text))

Max Activating Token Index: 798

Text #8

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.4437. Min Act: -0.0001

Data Index: 325100 (C4 (Web Text))

Max Activating Token Index: 205

Text #9

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.4398. Min Act: -0.0001

Data Index: 1072592 (C4 (Web Text))

Max Activating Token Index: 115

Text #10

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.4549. Min Act: -0.0001

Data Index: 1022025 (C4 (Web Text))

Max Activating Token Index: 178

Text #11

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.4063. Min Act: -0.0001

Data Index: 242992 (C4 (Web Text))

Max Activating Token Index: 755

Text #12

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.4378. Min Act: -0.0001

Data Index: 898597 (C4 (Web Text))

Max Activating Token Index: 386

Text #13

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.4367. Min Act: -0.0001

Data Index: 1246991 (C4 (Web Text))

Max Activating Token Index: 104

Text #14

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.4348. Min Act: -0.0001

Data Index: 540224 (C4 (Web Text))

Max Activating Token Index: 133

Text #15

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.4303. Min Act: -0.0001

Data Index: 372332 (C4 (Web Text))

Max Activating Token Index: 205

Text #16

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.3881. Min Act: -0.0001

Data Index: 774618 (C4 (Web Text))

Max Activating Token Index: 608

Text #17

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.4272. Min Act: -0.0001

Data Index: 433953 (C4 (Web Text))

Max Activating Token Index: 291

Text #18

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.4265. Min Act: -0.0001

Data Index: 542690 (C4 (Web Text))

Max Activating Token Index: 115

Text #19

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.4250. Min Act: -0.0001

Data Index: 58732 (C4 (Web Text))

Max Activating Token Index: 171