Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2004 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 3.0322. Min Range: -3.0322
Max Act: 3.0322. Min Act: -0.1700
Data Index: 1504651 (Python Code)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0322. Min Range: -3.0322
Max Act: 2.9373. Min Act: -0.1700
Data Index: 1546819 (Python Code)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0322. Min Range: -3.0322
Max Act: 2.9215. Min Act: -0.1700
Data Index: 1380141 (Python Code)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0322. Min Range: -3.0322
Max Act: 2.8897. Min Act: -0.1700
Data Index: 1387073 (Python Code)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0322. Min Range: -3.0322
Max Act: 2.9215. Min Act: -0.1700
Data Index: 1360792 (Python Code)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0322. Min Range: -3.0322
Max Act: 2.9056. Min Act: -0.1700
Data Index: 1631039 (Python Code)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0322. Min Range: -3.0322
Max Act: 2.8897. Min Act: -0.1700
Data Index: 1468762 (Python Code)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0322. Min Range: -3.0322
Max Act: 2.8739. Min Act: -0.1700
Data Index: 1653722 (Python Code)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0322. Min Range: -3.0322
Max Act: 2.8739. Min Act: -0.1700
Data Index: 1600998 (Python Code)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0322. Min Range: -3.0322
Max Act: 2.8580. Min Act: -0.1700
Data Index: 1368068 (Python Code)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0322. Min Range: -3.0322
Max Act: 2.8580. Min Act: -0.1700
Data Index: 1436830 (Python Code)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0322. Min Range: -3.0322
Max Act: 2.8739. Min Act: -0.1700
Data Index: 1361770 (Python Code)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0322. Min Range: -3.0322
Max Act: 2.8580. Min Act: -0.1700
Data Index: 1402895 (Python Code)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0322. Min Range: -3.0322
Max Act: 2.8421. Min Act: -0.1700
Data Index: 1438571 (Python Code)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0322. Min Range: -3.0322
Max Act: 2.8580. Min Act: -0.1700
Data Index: 1600133 (Python Code)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0322. Min Range: -3.0322
Max Act: 2.8421. Min Act: -0.1700
Data Index: 1519731 (Python Code)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0322. Min Range: -3.0322
Max Act: 2.8421. Min Act: -0.1648
Data Index: 1599666 (Python Code)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0322. Min Range: -3.0322
Max Act: 2.8421. Min Act: -0.1700
Data Index: 1573658 (Python Code)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0322. Min Range: -3.0322
Max Act: 2.8421. Min Act: -0.1700
Data Index: 1565557 (Python Code)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0322. Min Range: -3.0322
Max Act: 2.8421. Min Act: -0.1700
Data Index: 1374430 (Python Code)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #19