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

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

Neuron 262 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6074. Min Range: -0.6074

Max Act: 0.5985. Min Act: -0.0001

Data Index: 628374 (C4 (Web Text))

Max Activating Token Index: 173

Text #1

Max Range: 0.6074. Min Range: -0.6074

Max Act: 0.5819. Min Act: -0.0001

Data Index: 273961 (C4 (Web Text))

Max Activating Token Index: 689

Text #2

Max Range: 0.6074. Min Range: -0.6074

Max Act: 0.5749. Min Act: -0.0001

Data Index: 839524 (C4 (Web Text))

Max Activating Token Index: 363

Text #3

Max Range: 0.6074. Min Range: -0.6074

Max Act: 0.6074. Min Act: -0.0001

Data Index: 1413396 (Python Code)

Max Activating Token Index: 272

Text #4

Max Range: 0.6074. Min Range: -0.6074

Max Act: 0.5401. Min Act: -0.0001

Data Index: 1217323 (C4 (Web Text))

Max Activating Token Index: 301

Text #5

Max Range: 0.6074. Min Range: -0.6074

Max Act: 0.4650. Min Act: -0.0001

Data Index: 1195823 (C4 (Web Text))

Max Activating Token Index: 86

Text #6

Max Range: 0.6074. Min Range: -0.6074

Max Act: 0.5441. Min Act: -0.0001

Data Index: 254275 (C4 (Web Text))

Max Activating Token Index: 28

Text #7

Max Range: 0.6074. Min Range: -0.6074

Max Act: 0.4312. Min Act: -0.0001

Data Index: 1298754 (C4 (Web Text))

Max Activating Token Index: 763

Text #8

Max Range: 0.6074. Min Range: -0.6074

Max Act: 0.5420. Min Act: -0.0001

Data Index: 428087 (C4 (Web Text))

Max Activating Token Index: 621

Text #9

Max Range: 0.6074. Min Range: -0.6074

Max Act: 0.5047. Min Act: -0.0001

Data Index: 335089 (C4 (Web Text))

Max Activating Token Index: 853

Text #10

Max Range: 0.6074. Min Range: -0.6074

Max Act: 0.4784. Min Act: -0.0001

Data Index: 684119 (C4 (Web Text))

Max Activating Token Index: 599

Text #11

Max Range: 0.6074. Min Range: -0.6074

Max Act: 0.4908. Min Act: -0.0001

Data Index: 1279645 (C4 (Web Text))

Max Activating Token Index: 366

Text #12

Max Range: 0.6074. Min Range: -0.6074

Max Act: 0.5148. Min Act: -0.0001

Data Index: 712534 (C4 (Web Text))

Max Activating Token Index: 192

Text #13

Max Range: 0.6074. Min Range: -0.6074

Max Act: 0.4555. Min Act: -0.0001

Data Index: 860109 (C4 (Web Text))

Max Activating Token Index: 143

Text #14

Max Range: 0.6074. Min Range: -0.6074

Max Act: 0.4656. Min Act: -0.0001

Data Index: 21243 (C4 (Web Text))

Max Activating Token Index: 36

Text #15

Max Range: 0.6074. Min Range: -0.6074

Max Act: 0.4493. Min Act: -0.0001

Data Index: 485736 (C4 (Web Text))

Max Activating Token Index: 659

Text #16

Max Range: 0.6074. Min Range: -0.6074

Max Act: 0.4756. Min Act: -0.0001

Data Index: 368632 (C4 (Web Text))

Max Activating Token Index: 413

Text #17

Max Range: 0.6074. Min Range: -0.6074

Max Act: 0.4741. Min Act: -0.0001

Data Index: 1048471 (C4 (Web Text))

Max Activating Token Index: 688

Text #18

Max Range: 0.6074. Min Range: -0.6074

Max Act: 0.4580. Min Act: -0.0001

Data Index: 603302 (C4 (Web Text))

Max Activating Token Index: 279

Text #19

Max Range: 0.6074. Min Range: -0.6074

Max Act: 0.4734. Min Act: -0.0001

Data Index: 826299 (C4 (Web Text))

Max Activating Token Index: 929