Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1080 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.1774. Min Range: -4.1774
Max Act: 4.1774. Min Act: -0.1700
Data Index: 1452918 (Python Code)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1774. Min Range: -4.1774
Max Act: 4.1149. Min Act: -0.1700
Data Index: 1388260 (Python Code)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1774. Min Range: -4.1774
Max Act: 4.0524. Min Act: -0.1700
Data Index: 1523731 (Python Code)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1774. Min Range: -4.1774
Max Act: 4.0524. Min Act: -0.1700
Data Index: 1571707 (Python Code)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1774. Min Range: -4.1774
Max Act: 3.9899. Min Act: -0.1700
Data Index: 1649237 (Python Code)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1774. Min Range: -4.1774
Max Act: 3.9273. Min Act: -0.1700
Data Index: 362990 (C4 (Web Text))
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1774. Min Range: -4.1774
Max Act: 3.9273. Min Act: -0.1700
Data Index: 1363467 (Python Code)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1774. Min Range: -4.1774
Max Act: 3.9273. Min Act: -0.1700
Data Index: 1438576 (Python Code)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1774. Min Range: -4.1774
Max Act: 3.9273. Min Act: -0.1700
Data Index: 1412531 (Python Code)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1774. Min Range: -4.1774
Max Act: 3.9273. Min Act: -0.1700
Data Index: 1531614 (Python Code)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1774. Min Range: -4.1774
Max Act: 3.8961. Min Act: -0.1700
Data Index: 1144354 (C4 (Web Text))
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1774. Min Range: -4.1774
Max Act: 3.8648. Min Act: -0.1700
Data Index: 1413596 (Python Code)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1774. Min Range: -4.1774
Max Act: 3.8961. Min Act: -0.1700
Data Index: 1595585 (Python Code)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1774. Min Range: -4.1774
Max Act: 3.8961. Min Act: -0.1700
Data Index: 1621378 (Python Code)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1774. Min Range: -4.1774
Max Act: 3.9273. Min Act: -0.1700
Data Index: 1378006 (Python Code)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1774. Min Range: -4.1774
Max Act: 3.8022. Min Act: -0.1700
Data Index: 1454386 (Python Code)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1774. Min Range: -4.1774
Max Act: 3.8648. Min Act: -0.1700
Data Index: 435022 (C4 (Web Text))
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1774. Min Range: -4.1774
Max Act: 3.8335. Min Act: -0.1700
Data Index: 1546817 (Python Code)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1774. Min Range: -4.1774
Max Act: 3.8022. Min Act: -0.1700
Data Index: 1375672 (Python Code)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1774. Min Range: -4.1774
Max Act: 3.8022. Min Act: -0.1700
Data Index: 164767 (C4 (Web Text))
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #19