Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5166 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1808. Min Range: -2.1808

Max Act: 2.0717. Min Act: -0.0000

Data Index: 1168761 (C4 (Web Text))

Max Activating Token Index: 171

Text #1

Max Range: 2.1808. Min Range: -2.1808

Max Act: 2.1724. Min Act: -0.0000

Data Index: 1117223 (C4 (Web Text))

Max Activating Token Index: 450

Text #2

Max Range: 2.1808. Min Range: -2.1808

Max Act: 2.0658. Min Act: -0.0000

Data Index: 948355 (C4 (Web Text))

Max Activating Token Index: 416

Text #3

Max Range: 2.1808. Min Range: -2.1808

Max Act: 2.1808. Min Act: -0.0000

Data Index: 900827 (C4 (Web Text))

Max Activating Token Index: 277

Text #4

Max Range: 2.1808. Min Range: -2.1808

Max Act: 2.1758. Min Act: -0.0000

Data Index: 111494 (C4 (Web Text))

Max Activating Token Index: 500

Text #5

Max Range: 2.1808. Min Range: -2.1808

Max Act: 2.0417. Min Act: -0.0000

Data Index: 73465 (C4 (Web Text))

Max Activating Token Index: 533

Text #6

Max Range: 2.1808. Min Range: -2.1808

Max Act: 1.8435. Min Act: -0.0000

Data Index: 13375 (C4 (Web Text))

Max Activating Token Index: 224

Text #7

Max Range: 2.1808. Min Range: -2.1808

Max Act: 1.9224. Min Act: -0.0000

Data Index: 631320 (C4 (Web Text))

Max Activating Token Index: 478

Text #8

Max Range: 2.1808. Min Range: -2.1808

Max Act: 1.6475. Min Act: -0.0000

Data Index: 1312638 (C4 (Web Text))

Max Activating Token Index: 592

Text #9

Max Range: 2.1808. Min Range: -2.1808

Max Act: 1.6626. Min Act: -0.0000

Data Index: 604226 (C4 (Web Text))

Max Activating Token Index: 509

Text #10

Max Range: 2.1808. Min Range: -2.1808

Max Act: 1.4567. Min Act: -0.0000

Data Index: 510756 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 2.1808. Min Range: -2.1808

Max Act: 1.4545. Min Act: -0.0000

Data Index: 672539 (C4 (Web Text))

Max Activating Token Index: 254

Text #12

Max Range: 2.1808. Min Range: -2.1808

Max Act: 1.5324. Min Act: -0.0000

Data Index: 336570 (C4 (Web Text))

Max Activating Token Index: 62

Text #13

Max Range: 2.1808. Min Range: -2.1808

Max Act: 1.0624. Min Act: -0.0000

Data Index: 566385 (C4 (Web Text))

Max Activating Token Index: 306

Text #14

Max Range: 2.1808. Min Range: -2.1808

Max Act: 1.3939. Min Act: -0.0000

Data Index: 1645789 (Python Code)

Max Activating Token Index: 365

Text #15

Max Range: 2.1808. Min Range: -2.1808

Max Act: 1.2820. Min Act: -0.0000

Data Index: 588705 (C4 (Web Text))

Max Activating Token Index: 260

Text #16

Max Range: 2.1808. Min Range: -2.1808

Max Act: 1.2685. Min Act: -0.0000

Data Index: 1354381 (C4 (Web Text))

Max Activating Token Index: 198

Text #17

Max Range: 2.1808. Min Range: -2.1808

Max Act: 1.3606. Min Act: -0.0000

Data Index: 1223088 (C4 (Web Text))

Max Activating Token Index: 978

Text #18

Max Range: 2.1808. Min Range: -2.1808

Max Act: 1.2567. Min Act: -0.0000

Data Index: 925271 (C4 (Web Text))

Max Activating Token Index: 909

Text #19

Max Range: 2.1808. Min Range: -2.1808

Max Act: 1.2506. Min Act: -0.0000

Data Index: 322471 (C4 (Web Text))

Max Activating Token Index: 88