Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2019 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.1570. Min Range: -4.1570
Max Act: 4.1570. Min Act: -0.1700
Data Index: 1589146 (Python Code)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1570. Min Range: -4.1570
Max Act: 4.1258. Min Act: -0.1700
Data Index: 1489722 (Python Code)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1570. Min Range: -4.1570
Max Act: 3.9382. Min Act: -0.1700
Data Index: 1545540 (Python Code)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1570. Min Range: -4.1570
Max Act: 3.9382. Min Act: -0.1700
Data Index: 1393596 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1570. Min Range: -4.1570
Max Act: 3.8756. Min Act: -0.1700
Data Index: 1577560 (Python Code)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1570. Min Range: -4.1570
Max Act: 3.8444. Min Act: -0.1700
Data Index: 1422398 (Python Code)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1570. Min Range: -4.1570
Max Act: 3.8444. Min Act: -0.1700
Data Index: 1590705 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1570. Min Range: -4.1570
Max Act: 3.8756. Min Act: -0.1700
Data Index: 1406094 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1570. Min Range: -4.1570
Max Act: 3.8756. Min Act: -0.1700
Data Index: 1533650 (Python Code)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1570. Min Range: -4.1570
Max Act: 3.8444. Min Act: -0.1700
Data Index: 1599737 (Python Code)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1570. Min Range: -4.1570
Max Act: 3.8131. Min Act: -0.1700
Data Index: 1512973 (Python Code)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1570. Min Range: -4.1570
Max Act: 3.7818. Min Act: -0.1700
Data Index: 1383499 (Python Code)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1570. Min Range: -4.1570
Max Act: 3.7505. Min Act: -0.1700
Data Index: 1369837 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1570. Min Range: -4.1570
Max Act: 3.8131. Min Act: -0.1700
Data Index: 1550116 (Python Code)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1570. Min Range: -4.1570
Max Act: 3.7505. Min Act: -0.1700
Data Index: 1467807 (Python Code)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1570. Min Range: -4.1570
Max Act: 3.8131. Min Act: -0.1700
Data Index: 1505920 (Python Code)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1570. Min Range: -4.1570
Max Act: 3.7505. Min Act: -0.1700
Data Index: 1398879 (Python Code)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1570. Min Range: -4.1570
Max Act: 3.7505. Min Act: -0.1700
Data Index: 1513720 (Python Code)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1570. Min Range: -4.1570
Max Act: 3.7505. Min Act: -0.1700
Data Index: 1512487 (Python Code)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1570. Min Range: -4.1570
Max Act: 3.6879. Min Act: -0.1700
Data Index: 1405990 (Python Code)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #19