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

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

Neuron 5677 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8338. Min Range: -5.8338

Max Act: 5.7287. Min Act: -0.0000

Data Index: 863564 (C4 (Web Text))

Max Activating Token Index: 724

Text #1

Max Range: 5.8338. Min Range: -5.8338

Max Act: 5.3076. Min Act: -0.0000

Data Index: 352853 (C4 (Web Text))

Max Activating Token Index: 749

Text #2

Max Range: 5.8338. Min Range: -5.8338

Max Act: 5.8338. Min Act: -0.0000

Data Index: 1097322 (C4 (Web Text))

Max Activating Token Index: 842

Text #3

Max Range: 5.8338. Min Range: -5.8338

Max Act: 5.2468. Min Act: -0.0001

Data Index: 133509 (C4 (Web Text))

Max Activating Token Index: 990

Text #4

Max Range: 5.8338. Min Range: -5.8338

Max Act: 5.2088. Min Act: -0.0000

Data Index: 1130248 (C4 (Web Text))

Max Activating Token Index: 578

Text #5

Max Range: 5.8338. Min Range: -5.8338

Max Act: 5.2969. Min Act: -0.0001

Data Index: 956810 (C4 (Web Text))

Max Activating Token Index: 271

Text #6

Max Range: 5.8338. Min Range: -5.8338

Max Act: 4.8829. Min Act: -0.0001

Data Index: 1341634 (C4 (Web Text))

Max Activating Token Index: 642

Text #7

Max Range: 5.8338. Min Range: -5.8338

Max Act: 4.7986. Min Act: -0.0000

Data Index: 538269 (C4 (Web Text))

Max Activating Token Index: 432

Text #8

Max Range: 5.8338. Min Range: -5.8338

Max Act: 4.2189. Min Act: -0.0000

Data Index: 1266436 (C4 (Web Text))

Max Activating Token Index: 986

Text #9

Max Range: 5.8338. Min Range: -5.8338

Max Act: 3.7898. Min Act: -0.0000

Data Index: 1089462 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 5.8338. Min Range: -5.8338

Max Act: 3.9419. Min Act: -0.0000

Data Index: 1296395 (C4 (Web Text))

Max Activating Token Index: 560

Text #11

Max Range: 5.8338. Min Range: -5.8338

Max Act: 3.9581. Min Act: -0.0000

Data Index: 629014 (C4 (Web Text))

Max Activating Token Index: 288

Text #12

Max Range: 5.8338. Min Range: -5.8338

Max Act: 3.6123. Min Act: -0.0000

Data Index: 1310944 (C4 (Web Text))

Max Activating Token Index: 323

Text #13

Max Range: 5.8338. Min Range: -5.8338

Max Act: 3.3932. Min Act: -0.0001

Data Index: 1011000 (C4 (Web Text))

Max Activating Token Index: 482

Text #14

Max Range: 5.8338. Min Range: -5.8338

Max Act: 3.2311. Min Act: -0.0000

Data Index: 1042959 (C4 (Web Text))

Max Activating Token Index: 142

Text #15

Max Range: 5.8338. Min Range: -5.8338

Max Act: 3.1930. Min Act: -0.0001

Data Index: 977513 (C4 (Web Text))

Max Activating Token Index: 626

Text #16

Max Range: 5.8338. Min Range: -5.8338

Max Act: 3.2690. Min Act: -0.0000

Data Index: 456043 (C4 (Web Text))

Max Activating Token Index: 70

Text #17

Max Range: 5.8338. Min Range: -5.8338

Max Act: 3.2688. Min Act: -0.0000

Data Index: 511483 (C4 (Web Text))

Max Activating Token Index: 86

Text #18

Max Range: 5.8338. Min Range: -5.8338

Max Act: 3.4385. Min Act: -0.0000

Data Index: 1163860 (C4 (Web Text))

Max Activating Token Index: 61

Text #19

Max Range: 5.8338. Min Range: -5.8338

Max Act: 3.1364. Min Act: -0.0000

Data Index: 907177 (C4 (Web Text))

Max Activating Token Index: 159