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

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

Neuron 2094 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: 1.7831. Min Range: -1.7831

Max Act: 1.7831. Min Act: -0.0000

Data Index: 1268946 (C4 (Web Text))

Max Activating Token Index: 67

Text #1

Max Range: 1.7831. Min Range: -1.7831

Max Act: 1.6369. Min Act: -0.0000

Data Index: 558970 (C4 (Web Text))

Max Activating Token Index: 188

Text #2

Max Range: 1.7831. Min Range: -1.7831

Max Act: 1.6398. Min Act: -0.0000

Data Index: 1208683 (C4 (Web Text))

Max Activating Token Index: 630

Text #3

Max Range: 1.7831. Min Range: -1.7831

Max Act: 1.4671. Min Act: -0.0000

Data Index: 732944 (C4 (Web Text))

Max Activating Token Index: 260

Text #4

Max Range: 1.7831. Min Range: -1.7831

Max Act: 1.4899. Min Act: -0.0000

Data Index: 918597 (C4 (Web Text))

Max Activating Token Index: 546

Text #5

Max Range: 1.7831. Min Range: -1.7831

Max Act: 1.5061. Min Act: -0.0000

Data Index: 912354 (C4 (Web Text))

Max Activating Token Index: 212

Text #6

Max Range: 1.7831. Min Range: -1.7831

Max Act: 1.3975. Min Act: -0.0000

Data Index: 880718 (C4 (Web Text))

Max Activating Token Index: 280

Text #7

Max Range: 1.7831. Min Range: -1.7831

Max Act: 1.3458. Min Act: -0.0000

Data Index: 294867 (C4 (Web Text))

Max Activating Token Index: 707

Text #8

Max Range: 1.7831. Min Range: -1.7831

Max Act: 1.3805. Min Act: -0.0000

Data Index: 703738 (C4 (Web Text))

Max Activating Token Index: 556

Text #9

Max Range: 1.7831. Min Range: -1.7831

Max Act: 1.4382. Min Act: -0.0000

Data Index: 1006439 (C4 (Web Text))

Max Activating Token Index: 31

Text #10

Max Range: 1.7831. Min Range: -1.7831

Max Act: 1.4213. Min Act: -0.0000

Data Index: 449362 (C4 (Web Text))

Max Activating Token Index: 457

Text #11

Max Range: 1.7831. Min Range: -1.7831

Max Act: 1.3369. Min Act: -0.0000

Data Index: 201769 (C4 (Web Text))

Max Activating Token Index: 418

Text #12

Max Range: 1.7831. Min Range: -1.7831

Max Act: 1.2733. Min Act: -0.0000

Data Index: 884003 (C4 (Web Text))

Max Activating Token Index: 887

Text #13

Max Range: 1.7831. Min Range: -1.7831

Max Act: 1.2705. Min Act: -0.0000

Data Index: 133505 (C4 (Web Text))

Max Activating Token Index: 946

Text #14

Max Range: 1.7831. Min Range: -1.7831

Max Act: 1.1832. Min Act: -0.0000

Data Index: 924166 (C4 (Web Text))

Max Activating Token Index: 959

Text #15

Max Range: 1.7831. Min Range: -1.7831

Max Act: 1.3098. Min Act: -0.0000

Data Index: 419883 (C4 (Web Text))

Max Activating Token Index: 312

Text #16

Max Range: 1.7831. Min Range: -1.7831

Max Act: 1.2796. Min Act: -0.0000

Data Index: 920608 (C4 (Web Text))

Max Activating Token Index: 80

Text #17

Max Range: 1.7831. Min Range: -1.7831

Max Act: 1.2434. Min Act: -0.0000

Data Index: 450330 (C4 (Web Text))

Max Activating Token Index: 400

Text #18

Max Range: 1.7831. Min Range: -1.7831

Max Act: 1.2518. Min Act: -0.0000

Data Index: 1224150 (C4 (Web Text))

Max Activating Token Index: 964

Text #19

Max Range: 1.7831. Min Range: -1.7831

Max Act: 1.3434. Min Act: -0.0000

Data Index: 938817 (C4 (Web Text))

Max Activating Token Index: 974