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

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

Neuron 1537 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: 3.2842. Min Range: -3.2842

Max Act: 3.1882. Min Act: -0.0000

Data Index: 912518 (C4 (Web Text))

Max Activating Token Index: 760

Text #1

Max Range: 3.2842. Min Range: -3.2842

Max Act: 3.2106. Min Act: -0.0000

Data Index: 533848 (C4 (Web Text))

Max Activating Token Index: 918

Text #2

Max Range: 3.2842. Min Range: -3.2842

Max Act: 3.2842. Min Act: -0.0000

Data Index: 272714 (C4 (Web Text))

Max Activating Token Index: 994

Text #3

Max Range: 3.2842. Min Range: -3.2842

Max Act: 2.8590. Min Act: -0.0000

Data Index: 1117125 (C4 (Web Text))

Max Activating Token Index: 951

Text #4

Max Range: 3.2842. Min Range: -3.2842

Max Act: 3.0101. Min Act: -0.0000

Data Index: 1549195 (Python Code)

Max Activating Token Index: 877

Text #5

Max Range: 3.2842. Min Range: -3.2842

Max Act: 3.0312. Min Act: -0.0000

Data Index: 1547584 (Python Code)

Max Activating Token Index: 332

Text #6

Max Range: 3.2842. Min Range: -3.2842

Max Act: 2.9047. Min Act: -0.0000

Data Index: 51145 (C4 (Web Text))

Max Activating Token Index: 691

Text #7

Max Range: 3.2842. Min Range: -3.2842

Max Act: 2.7280. Min Act: -0.0000

Data Index: 1029480 (C4 (Web Text))

Max Activating Token Index: 690

Text #8

Max Range: 3.2842. Min Range: -3.2842

Max Act: 2.5487. Min Act: -0.0000

Data Index: 1611885 (Python Code)

Max Activating Token Index: 259

Text #9

Max Range: 3.2842. Min Range: -3.2842

Max Act: 2.6189. Min Act: -0.0000

Data Index: 1443622 (Python Code)

Max Activating Token Index: 627

Text #10

Max Range: 3.2842. Min Range: -3.2842

Max Act: 2.5554. Min Act: -0.0000

Data Index: 581520 (C4 (Web Text))

Max Activating Token Index: 246

Text #11

Max Range: 3.2842. Min Range: -3.2842

Max Act: 2.5092. Min Act: -0.0000

Data Index: 1400317 (Python Code)

Max Activating Token Index: 223

Text #12

Max Range: 3.2842. Min Range: -3.2842

Max Act: 2.4428. Min Act: -0.0000

Data Index: 1427767 (Python Code)

Max Activating Token Index: 773

Text #13

Max Range: 3.2842. Min Range: -3.2842

Max Act: 2.2752. Min Act: -0.0000

Data Index: 286286 (C4 (Web Text))

Max Activating Token Index: 527

Text #14

Max Range: 3.2842. Min Range: -3.2842

Max Act: 2.1257. Min Act: -0.0000

Data Index: 1490970 (Python Code)

Max Activating Token Index: 997

Text #15

Max Range: 3.2842. Min Range: -3.2842

Max Act: 2.3310. Min Act: -0.0000

Data Index: 1378061 (Python Code)

Max Activating Token Index: 161

Text #16

Max Range: 3.2842. Min Range: -3.2842

Max Act: 2.3265. Min Act: -0.0000

Data Index: 964432 (C4 (Web Text))

Max Activating Token Index: 231

Text #17

Max Range: 3.2842. Min Range: -3.2842

Max Act: 2.4652. Min Act: -0.0000

Data Index: 469494 (C4 (Web Text))

Max Activating Token Index: 233

Text #18

Max Range: 3.2842. Min Range: -3.2842

Max Act: 2.3354. Min Act: -0.0000

Data Index: 1623603 (Python Code)

Max Activating Token Index: 82

Text #19

Max Range: 3.2842. Min Range: -3.2842

Max Act: 2.3329. Min Act: -0.0000

Data Index: 1368803 (Python Code)

Max Activating Token Index: 728