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

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

Neuron 2203 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9475. Min Range: -1.9475

Max Act: 1.9475. Min Act: -0.0001

Data Index: 669309 (C4 (Web Text))

Max Activating Token Index: 138

Text #1

Max Range: 1.9475. Min Range: -1.9475

Max Act: 1.8298. Min Act: -0.0001

Data Index: 441944 (C4 (Web Text))

Max Activating Token Index: 878

Text #2

Max Range: 1.9475. Min Range: -1.9475

Max Act: 1.7778. Min Act: -0.0000

Data Index: 774941 (C4 (Web Text))

Max Activating Token Index: 152

Text #3

Max Range: 1.9475. Min Range: -1.9475

Max Act: 1.6145. Min Act: -0.0000

Data Index: 264081 (C4 (Web Text))

Max Activating Token Index: 999

Text #4

Max Range: 1.9475. Min Range: -1.9475

Max Act: 1.7659. Min Act: -0.0001

Data Index: 1350795 (C4 (Web Text))

Max Activating Token Index: 817

Text #5

Max Range: 1.9475. Min Range: -1.9475

Max Act: 1.6524. Min Act: -0.0000

Data Index: 32045 (C4 (Web Text))

Max Activating Token Index: 653

Text #6

Max Range: 1.9475. Min Range: -1.9475

Max Act: 1.5553. Min Act: -0.0001

Data Index: 597122 (C4 (Web Text))

Max Activating Token Index: 62

Text #7

Max Range: 1.9475. Min Range: -1.9475

Max Act: 1.5446. Min Act: -0.0000

Data Index: 514421 (C4 (Web Text))

Max Activating Token Index: 236

Text #8

Max Range: 1.9475. Min Range: -1.9475

Max Act: 1.5048. Min Act: -0.0000

Data Index: 138452 (C4 (Web Text))

Max Activating Token Index: 421

Text #9

Max Range: 1.9475. Min Range: -1.9475

Max Act: 1.4721. Min Act: -0.0001

Data Index: 80274 (C4 (Web Text))

Max Activating Token Index: 655

Text #10

Max Range: 1.9475. Min Range: -1.9475

Max Act: 1.4158. Min Act: -0.0000

Data Index: 1324724 (C4 (Web Text))

Max Activating Token Index: 235

Text #11

Max Range: 1.9475. Min Range: -1.9475

Max Act: 1.3601. Min Act: -0.0000

Data Index: 67735 (C4 (Web Text))

Max Activating Token Index: 400

Text #12

Max Range: 1.9475. Min Range: -1.9475

Max Act: 1.2822. Min Act: -0.0001

Data Index: 1476375 (Python Code)

Max Activating Token Index: 29

Text #13

Max Range: 1.9475. Min Range: -1.9475

Max Act: 1.2687. Min Act: -0.0001

Data Index: 1363252 (Python Code)

Max Activating Token Index: 143

Text #14

Max Range: 1.9475. Min Range: -1.9475

Max Act: 1.2280. Min Act: -0.0000

Data Index: 282114 (C4 (Web Text))

Max Activating Token Index: 452

Text #15

Max Range: 1.9475. Min Range: -1.9475

Max Act: 1.2205. Min Act: -0.0001

Data Index: 604074 (C4 (Web Text))

Max Activating Token Index: 340

Text #16

Max Range: 1.9475. Min Range: -1.9475

Max Act: 1.2174. Min Act: -0.0000

Data Index: 203023 (C4 (Web Text))

Max Activating Token Index: 256

Text #17

Max Range: 1.9475. Min Range: -1.9475

Max Act: 1.1688. Min Act: -0.0001

Data Index: 306994 (C4 (Web Text))

Max Activating Token Index: 532

Text #18

Max Range: 1.9475. Min Range: -1.9475

Max Act: 1.1305. Min Act: -0.0001

Data Index: 738769 (C4 (Web Text))

Max Activating Token Index: 449

Text #19

Max Range: 1.9475. Min Range: -1.9475

Max Act: 1.0988. Min Act: -0.0001

Data Index: 534162 (C4 (Web Text))

Max Activating Token Index: 568