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

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

Neuron 3922 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7937. Min Range: -2.7937

Max Act: 2.7937. Min Act: -0.0000

Data Index: 1079817 (C4 (Web Text))

Max Activating Token Index: 603

Text #1

Max Range: 2.7937. Min Range: -2.7937

Max Act: 2.2372. Min Act: -0.0000

Data Index: 1284899 (C4 (Web Text))

Max Activating Token Index: 6

Text #2

Max Range: 2.7937. Min Range: -2.7937

Max Act: 1.9919. Min Act: -0.0000

Data Index: 928071 (C4 (Web Text))

Max Activating Token Index: 286

Text #3

Max Range: 2.7937. Min Range: -2.7937

Max Act: 2.1612. Min Act: -0.0000

Data Index: 1505342 (Python Code)

Max Activating Token Index: 493

Text #4

Max Range: 2.7937. Min Range: -2.7937

Max Act: 2.2337. Min Act: -0.0000

Data Index: 1290138 (C4 (Web Text))

Max Activating Token Index: 883

Text #5

Max Range: 2.7937. Min Range: -2.7937

Max Act: 2.2137. Min Act: -0.0000

Data Index: 195873 (C4 (Web Text))

Max Activating Token Index: 173

Text #6

Max Range: 2.7937. Min Range: -2.7937

Max Act: 1.9818. Min Act: -0.0000

Data Index: 1045053 (C4 (Web Text))

Max Activating Token Index: 912

Text #7

Max Range: 2.7937. Min Range: -2.7937

Max Act: 2.0526. Min Act: -0.0000

Data Index: 525541 (C4 (Web Text))

Max Activating Token Index: 939

Text #8

Max Range: 2.7937. Min Range: -2.7937

Max Act: 2.0794. Min Act: -0.0000

Data Index: 1327667 (C4 (Web Text))

Max Activating Token Index: 347

Text #9

Max Range: 2.7937. Min Range: -2.7937

Max Act: 1.9920. Min Act: -0.0000

Data Index: 526510 (C4 (Web Text))

Max Activating Token Index: 571

Text #10

Max Range: 2.7937. Min Range: -2.7937

Max Act: 1.9278. Min Act: -0.0000

Data Index: 87038 (C4 (Web Text))

Max Activating Token Index: 268

Text #11

Max Range: 2.7937. Min Range: -2.7937

Max Act: 1.9726. Min Act: -0.0000

Data Index: 557105 (C4 (Web Text))

Max Activating Token Index: 497

Text #12

Max Range: 2.7937. Min Range: -2.7937

Max Act: 1.9450. Min Act: -0.0000

Data Index: 1105475 (C4 (Web Text))

Max Activating Token Index: 361

Text #13

Max Range: 2.7937. Min Range: -2.7937

Max Act: 1.8081. Min Act: -0.0000

Data Index: 101229 (C4 (Web Text))

Max Activating Token Index: 469

Text #14

Max Range: 2.7937. Min Range: -2.7937

Max Act: 1.9663. Min Act: -0.0000

Data Index: 711109 (C4 (Web Text))

Max Activating Token Index: 679

Text #15

Max Range: 2.7937. Min Range: -2.7937

Max Act: 2.0494. Min Act: -0.0000

Data Index: 1199786 (C4 (Web Text))

Max Activating Token Index: 838

Text #16

Max Range: 2.7937. Min Range: -2.7937

Max Act: 2.0805. Min Act: -0.0000

Data Index: 8136 (C4 (Web Text))

Max Activating Token Index: 142

Text #17

Max Range: 2.7937. Min Range: -2.7937

Max Act: 1.8704. Min Act: -0.0000

Data Index: 581821 (C4 (Web Text))

Max Activating Token Index: 414

Text #18

Max Range: 2.7937. Min Range: -2.7937

Max Act: 1.9785. Min Act: -0.0000

Data Index: 1342053 (C4 (Web Text))

Max Activating Token Index: 294

Text #19

Max Range: 2.7937. Min Range: -2.7937

Max Act: 1.8613. Min Act: -0.0000

Data Index: 562599 (C4 (Web Text))

Max Activating Token Index: 549