Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 2042 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.4093. Min Range: -0.4093

Max Act: 0.4093. Min Act: -0.0002

Data Index: 126607 (C4 (Web Text))

Max Activating Token Index: 915

Text #1

Max Range: 0.4093. Min Range: -0.4093

Max Act: 0.2832. Min Act: -0.0002

Data Index: 347964 (C4 (Web Text))

Max Activating Token Index: 316

Text #2

Max Range: 0.4093. Min Range: -0.4093

Max Act: 0.2863. Min Act: -0.0002

Data Index: 667866 (C4 (Web Text))

Max Activating Token Index: 406

Text #3

Max Range: 0.4093. Min Range: -0.4093

Max Act: 0.2734. Min Act: -0.0002

Data Index: 1049052 (C4 (Web Text))

Max Activating Token Index: 947

Text #4

Max Range: 0.4093. Min Range: -0.4093

Max Act: 0.2895. Min Act: -0.0002

Data Index: 1161746 (C4 (Web Text))

Max Activating Token Index: 524

Text #5

Max Range: 0.4093. Min Range: -0.4093

Max Act: 0.2762. Min Act: -0.0002

Data Index: 1302264 (C4 (Web Text))

Max Activating Token Index: 208

Text #6

Max Range: 0.4093. Min Range: -0.4093

Max Act: 0.2688. Min Act: -0.0002

Data Index: 145659 (C4 (Web Text))

Max Activating Token Index: 124

Text #7

Max Range: 0.4093. Min Range: -0.4093

Max Act: 0.2647. Min Act: -0.0002

Data Index: 612721 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 0.4093. Min Range: -0.4093

Max Act: 0.2716. Min Act: -0.0002

Data Index: 1353912 (C4 (Web Text))

Max Activating Token Index: 817

Text #9

Max Range: 0.4093. Min Range: -0.4093

Max Act: 0.2347. Min Act: -0.0002

Data Index: 146860 (C4 (Web Text))

Max Activating Token Index: 966

Text #10

Max Range: 0.4093. Min Range: -0.4093

Max Act: 0.2451. Min Act: -0.0002

Data Index: 1106417 (C4 (Web Text))

Max Activating Token Index: 94

Text #11

Max Range: 0.4093. Min Range: -0.4093

Max Act: 0.2335. Min Act: -0.0002

Data Index: 621237 (C4 (Web Text))

Max Activating Token Index: 725

Text #12

Max Range: 0.4093. Min Range: -0.4093

Max Act: 0.2572. Min Act: -0.0002

Data Index: 1029574 (C4 (Web Text))

Max Activating Token Index: 320

Text #13

Max Range: 0.4093. Min Range: -0.4093

Max Act: 0.2314. Min Act: -0.0002

Data Index: 1023713 (C4 (Web Text))

Max Activating Token Index: 842

Text #14

Max Range: 0.4093. Min Range: -0.4093

Max Act: 0.2370. Min Act: -0.0002

Data Index: 496403 (C4 (Web Text))

Max Activating Token Index: 221

Text #15

Max Range: 0.4093. Min Range: -0.4093

Max Act: 0.2277. Min Act: -0.0002

Data Index: 997418 (C4 (Web Text))

Max Activating Token Index: 903

Text #16

Max Range: 0.4093. Min Range: -0.4093

Max Act: 0.2403. Min Act: -0.0002

Data Index: 1009926 (C4 (Web Text))

Max Activating Token Index: 663

Text #17

Max Range: 0.4093. Min Range: -0.4093

Max Act: 0.2436. Min Act: -0.0002

Data Index: 1305664 (C4 (Web Text))

Max Activating Token Index: 742

Text #18

Max Range: 0.4093. Min Range: -0.4093

Max Act: 0.2382. Min Act: -0.0002

Data Index: 153928 (C4 (Web Text))

Max Activating Token Index: 944

Text #19

Max Range: 0.4093. Min Range: -0.4093

Max Act: 0.2298. Min Act: -0.0002

Data Index: 1292265 (C4 (Web Text))

Max Activating Token Index: 795