Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1749 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.5844. Min Range: -3.5844
Max Act: 3.5844. Min Act: -0.1700
Data Index: 1475538 (Python Code)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5844. Min Range: -3.5844
Max Act: 3.4748. Min Act: -0.1700
Data Index: 1429795 (Python Code)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5844. Min Range: -3.5844
Max Act: 3.4278. Min Act: -0.1700
Data Index: 1433422 (Python Code)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5844. Min Range: -3.5844
Max Act: 3.4434. Min Act: -0.1700
Data Index: 1501622 (Python Code)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5844. Min Range: -3.5844
Max Act: 3.4121. Min Act: -0.1700
Data Index: 1374408 (Python Code)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5844. Min Range: -3.5844
Max Act: 3.4748. Min Act: -0.1700
Data Index: 1444913 (Python Code)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5844. Min Range: -3.5844
Max Act: 3.4278. Min Act: -0.1700
Data Index: 1634140 (Python Code)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5844. Min Range: -3.5844
Max Act: 3.4434. Min Act: -0.1700
Data Index: 1655691 (Python Code)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5844. Min Range: -3.5844
Max Act: 3.4278. Min Act: -0.1700
Data Index: 1655721 (Python Code)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5844. Min Range: -3.5844
Max Act: 3.4278. Min Act: -0.1700
Data Index: 1418054 (Python Code)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5844. Min Range: -3.5844
Max Act: 3.4278. Min Act: -0.1700
Data Index: 1478945 (Python Code)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5844. Min Range: -3.5844
Max Act: 3.4278. Min Act: -0.1700
Data Index: 1416829 (Python Code)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5844. Min Range: -3.5844
Max Act: 3.3022. Min Act: -0.1700
Data Index: 1572532 (Python Code)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5844. Min Range: -3.5844
Max Act: 3.4121. Min Act: -0.1700
Data Index: 1480856 (Python Code)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5844. Min Range: -3.5844
Max Act: 3.4121. Min Act: -0.1700
Data Index: 1435554 (Python Code)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5844. Min Range: -3.5844
Max Act: 3.4121. Min Act: -0.1700
Data Index: 1499414 (Python Code)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5844. Min Range: -3.5844
Max Act: 3.4278. Min Act: -0.1700
Data Index: 1614510 (Python Code)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5844. Min Range: -3.5844
Max Act: 3.4121. Min Act: -0.1700
Data Index: 1458484 (Python Code)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5844. Min Range: -3.5844
Max Act: 3.3493. Min Act: -0.1700
Data Index: 1543968 (Python Code)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5844. Min Range: -3.5844
Max Act: 3.3336. Min Act: -0.1700
Data Index: 1529070 (Python Code)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #19