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

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

Neuron 3323 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 2.0443. Min Range: -2.0443

Max Act: 2.0443. Min Act: -0.0002

Data Index: 1193476 (C4 (Web Text))

Max Activating Token Index: 114

Text #1

Max Range: 2.0443. Min Range: -2.0443

Max Act: 1.9608. Min Act: -0.0002

Data Index: 729185 (C4 (Web Text))

Max Activating Token Index: 239

Text #2

Max Range: 2.0443. Min Range: -2.0443

Max Act: 1.8865. Min Act: -0.0002

Data Index: 1188761 (C4 (Web Text))

Max Activating Token Index: 309

Text #3

Max Range: 2.0443. Min Range: -2.0443

Max Act: 1.8907. Min Act: -0.0002

Data Index: 1358666 (C4 (Web Text))

Max Activating Token Index: 752

Text #4

Max Range: 2.0443. Min Range: -2.0443

Max Act: 1.8288. Min Act: -0.0002

Data Index: 476462 (C4 (Web Text))

Max Activating Token Index: 262

Text #5

Max Range: 2.0443. Min Range: -2.0443

Max Act: 1.8102. Min Act: -0.0002

Data Index: 73078 (C4 (Web Text))

Max Activating Token Index: 649

Text #6

Max Range: 2.0443. Min Range: -2.0443

Max Act: 1.8286. Min Act: -0.0002

Data Index: 515453 (C4 (Web Text))

Max Activating Token Index: 74

Text #7

Max Range: 2.0443. Min Range: -2.0443

Max Act: 1.7640. Min Act: -0.0002

Data Index: 404567 (C4 (Web Text))

Max Activating Token Index: 162

Text #8

Max Range: 2.0443. Min Range: -2.0443

Max Act: 1.7605. Min Act: -0.0002

Data Index: 521874 (C4 (Web Text))

Max Activating Token Index: 454

Text #9

Max Range: 2.0443. Min Range: -2.0443

Max Act: 1.7960. Min Act: -0.0002

Data Index: 116657 (C4 (Web Text))

Max Activating Token Index: 804

Text #10

Max Range: 2.0443. Min Range: -2.0443

Max Act: 1.7696. Min Act: -0.0002

Data Index: 160497 (C4 (Web Text))

Max Activating Token Index: 131

Text #11

Max Range: 2.0443. Min Range: -2.0443

Max Act: 1.7267. Min Act: -0.0002

Data Index: 1110758 (C4 (Web Text))

Max Activating Token Index: 624

Text #12

Max Range: 2.0443. Min Range: -2.0443

Max Act: 1.7158. Min Act: -0.0003

Data Index: 1347746 (C4 (Web Text))

Max Activating Token Index: 592

Text #13

Max Range: 2.0443. Min Range: -2.0443

Max Act: 1.6884. Min Act: -0.0002

Data Index: 554707 (C4 (Web Text))

Max Activating Token Index: 705

Text #14

Max Range: 2.0443. Min Range: -2.0443

Max Act: 1.6539. Min Act: -0.0002

Data Index: 463240 (C4 (Web Text))

Max Activating Token Index: 940

Text #15

Max Range: 2.0443. Min Range: -2.0443

Max Act: 1.6185. Min Act: -0.0002

Data Index: 1201145 (C4 (Web Text))

Max Activating Token Index: 839

Text #16

Max Range: 2.0443. Min Range: -2.0443

Max Act: 1.6015. Min Act: -0.0002

Data Index: 400363 (C4 (Web Text))

Max Activating Token Index: 452

Text #17

Max Range: 2.0443. Min Range: -2.0443

Max Act: 1.6277. Min Act: -0.0002

Data Index: 1068155 (C4 (Web Text))

Max Activating Token Index: 720

Text #18

Max Range: 2.0443. Min Range: -2.0443

Max Act: 1.5893. Min Act: -0.0002

Data Index: 1091951 (C4 (Web Text))

Max Activating Token Index: 909

Text #19

Max Range: 2.0443. Min Range: -2.0443

Max Act: 1.5682. Min Act: -0.0002

Data Index: 286250 (C4 (Web Text))

Max Activating Token Index: 801