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

Dataset: The Pile

Neuron 1994 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5348. Min Range: -1.5348

Max Act: 1.5348. Min Act: -0.0000

Data Index: 938989 (The Pile)

Max Activating Token Index: 67

Text #1

Max Range: 1.5348. Min Range: -1.5348

Max Act: 1.4831. Min Act: -0.0000

Data Index: 123775 (The Pile)

Max Activating Token Index: 89

Text #2

Max Range: 1.5348. Min Range: -1.5348

Max Act: 1.4462. Min Act: -0.0000

Data Index: 1075328 (The Pile)

Max Activating Token Index: 84

Text #3

Max Range: 1.5348. Min Range: -1.5348

Max Act: 1.3386. Min Act: -0.0000

Data Index: 1427753 (The Pile)

Max Activating Token Index: 768

Text #4

Max Range: 1.5348. Min Range: -1.5348

Max Act: 1.3615. Min Act: -0.0000

Data Index: 489903 (The Pile)

Max Activating Token Index: 206

Text #5

Max Range: 1.5348. Min Range: -1.5348

Max Act: 1.3677. Min Act: -0.0000

Data Index: 1013712 (The Pile)

Max Activating Token Index: 355

Text #6

Max Range: 1.5348. Min Range: -1.5348

Max Act: 1.2872. Min Act: -0.0000

Data Index: 1793309 (The Pile)

Max Activating Token Index: 182

Text #7

Max Range: 1.5348. Min Range: -1.5348

Max Act: 1.3284. Min Act: -0.0000

Data Index: 776013 (The Pile)

Max Activating Token Index: 199

Text #8

Max Range: 1.5348. Min Range: -1.5348

Max Act: 1.1411. Min Act: -0.0000

Data Index: 764804 (The Pile)

Max Activating Token Index: 687

Text #9

Max Range: 1.5348. Min Range: -1.5348

Max Act: 1.2818. Min Act: -0.0000

Data Index: 877263 (The Pile)

Max Activating Token Index: 423

Text #10

Max Range: 1.5348. Min Range: -1.5348

Max Act: 1.2042. Min Act: -0.0000

Data Index: 27299 (The Pile)

Max Activating Token Index: 156

Text #11

Max Range: 1.5348. Min Range: -1.5348

Max Act: 1.2932. Min Act: -0.0000

Data Index: 1056354 (The Pile)

Max Activating Token Index: 471

Text #12

Max Range: 1.5348. Min Range: -1.5348

Max Act: 1.1668. Min Act: -0.0000

Data Index: 491701 (The Pile)

Max Activating Token Index: 870

Text #13

Max Range: 1.5348. Min Range: -1.5348

Max Act: 1.2520. Min Act: -0.0000

Data Index: 1720534 (The Pile)

Max Activating Token Index: 226

Text #14

Max Range: 1.5348. Min Range: -1.5348

Max Act: 1.2110. Min Act: -0.0000

Data Index: 90566 (The Pile)

Max Activating Token Index: 260

Text #15

Max Range: 1.5348. Min Range: -1.5348

Max Act: 1.1661. Min Act: -0.0000

Data Index: 1187341 (The Pile)

Max Activating Token Index: 479

Text #16

Max Range: 1.5348. Min Range: -1.5348

Max Act: 1.2063. Min Act: -0.0000

Data Index: 1423199 (The Pile)

Max Activating Token Index: 685

Text #17

Max Range: 1.5348. Min Range: -1.5348

Max Act: 1.1318. Min Act: -0.0000

Data Index: 401796 (The Pile)

Max Activating Token Index: 159

Text #18

Max Range: 1.5348. Min Range: -1.5348

Max Act: 1.1723. Min Act: -0.0000

Data Index: 703255 (The Pile)

Max Activating Token Index: 343

Text #19

Max Range: 1.5348. Min Range: -1.5348

Max Act: 1.1263. Min Act: -0.0000

Data Index: 895740 (The Pile)

Max Activating Token Index: 753