Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2007 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.4788. Min Range: -2.4788
Max Act: 2.4788. Min Act: -0.1700
Data Index: 1513992 (Python Code)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4788. Min Range: -2.4788
Max Act: 2.4301. Min Act: -0.1700
Data Index: 1412710 (Python Code)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4788. Min Range: -2.4788
Max Act: 2.3648. Min Act: -0.1700
Data Index: 1605596 (Python Code)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4788. Min Range: -2.4788
Max Act: 2.3648. Min Act: -0.1700
Data Index: 1383438 (Python Code)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4788. Min Range: -2.4788
Max Act: 2.3648. Min Act: -0.1700
Data Index: 1407987 (Python Code)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4788. Min Range: -2.4788
Max Act: 2.3485. Min Act: -0.1700
Data Index: 1485656 (Python Code)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4788. Min Range: -2.4788
Max Act: 2.3485. Min Act: -0.1700
Data Index: 1460555 (Python Code)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4788. Min Range: -2.4788
Max Act: 2.3321. Min Act: -0.1700
Data Index: 1654428 (Python Code)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4788. Min Range: -2.4788
Max Act: 2.3485. Min Act: -0.1700
Data Index: 1464626 (Python Code)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4788. Min Range: -2.4788
Max Act: 2.3321. Min Act: -0.1700
Data Index: 1486861 (Python Code)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4788. Min Range: -2.4788
Max Act: 2.3157. Min Act: -0.1700
Data Index: 1646753 (Python Code)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4788. Min Range: -2.4788
Max Act: 2.3157. Min Act: -0.1700
Data Index: 1373949 (Python Code)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4788. Min Range: -2.4788
Max Act: 2.3157. Min Act: -0.1700
Data Index: 1392385 (Python Code)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4788. Min Range: -2.4788
Max Act: 2.3157. Min Act: -0.1700
Data Index: 1435157 (Python Code)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4788. Min Range: -2.4788
Max Act: 2.3157. Min Act: -0.1700
Data Index: 1639682 (Python Code)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4788. Min Range: -2.4788
Max Act: 2.3157. Min Act: -0.1700
Data Index: 1641407 (Python Code)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4788. Min Range: -2.4788
Max Act: 2.3157. Min Act: -0.1700
Data Index: 1447041 (Python Code)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4788. Min Range: -2.4788
Max Act: 2.2992. Min Act: -0.1700
Data Index: 1476236 (Python Code)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4788. Min Range: -2.4788
Max Act: 2.2992. Min Act: -0.1700
Data Index: 1413461 (Python Code)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4788. Min Range: -2.4788
Max Act: 2.3157. Min Act: -0.1700
Data Index: 1372665 (Python Code)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #19