Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1779 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.0561. Min Range: -4.0561
Max Act: 4.0561. Min Act: -0.1700
Data Index: 565051 (C4 (Web Text))
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0561. Min Range: -4.0561
Max Act: 3.8841. Min Act: -0.1700
Data Index: 346248 (C4 (Web Text))
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0561. Min Range: -4.0561
Max Act: 3.8841. Min Act: -0.1700
Data Index: 1596626 (Python Code)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0561. Min Range: -4.0561
Max Act: 3.7747. Min Act: -0.1699
Data Index: 810006 (C4 (Web Text))
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0561. Min Range: -4.0561
Max Act: 3.7121. Min Act: -0.1700
Data Index: 1552528 (Python Code)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0561. Min Range: -4.0561
Max Act: 3.6025. Min Act: -0.1700
Data Index: 480321 (C4 (Web Text))
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0561. Min Range: -4.0561
Max Act: 3.4929. Min Act: -0.1700
Data Index: 1543860 (Python Code)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0561. Min Range: -4.0561
Max Act: 3.3988. Min Act: -0.1700
Data Index: 1396292 (Python Code)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0561. Min Range: -4.0561
Max Act: 3.3361. Min Act: -0.1700
Data Index: 946054 (C4 (Web Text))
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0561. Min Range: -4.0561
Max Act: 3.2261. Min Act: -0.1700
Data Index: 1454956 (Python Code)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0561. Min Range: -4.0561
Max Act: 3.1946. Min Act: -0.1700
Data Index: 1404314 (Python Code)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0561. Min Range: -4.0561
Max Act: 3.1946. Min Act: -0.1700
Data Index: 531672 (C4 (Web Text))
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0561. Min Range: -4.0561
Max Act: 3.1474. Min Act: -0.1700
Data Index: 1542108 (Python Code)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0561. Min Range: -4.0561
Max Act: 3.1474. Min Act: -0.1700
Data Index: 1633759 (Python Code)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0561. Min Range: -4.0561
Max Act: 3.1159. Min Act: -0.1700
Data Index: 691694 (C4 (Web Text))
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0561. Min Range: -4.0561
Max Act: 3.1316. Min Act: -0.1700
Data Index: 1534278 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0561. Min Range: -4.0561
Max Act: 3.0686. Min Act: -0.1700
Data Index: 573070 (C4 (Web Text))
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0561. Min Range: -4.0561
Max Act: 3.0370. Min Act: -0.1700
Data Index: 1022510 (C4 (Web Text))
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0561. Min Range: -4.0561
Max Act: 3.0212. Min Act: -0.1700
Data Index: 321225 (C4 (Web Text))
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0561. Min Range: -4.0561
Max Act: 3.0370. Min Act: -0.1700
Data Index: 408626 (C4 (Web Text))
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #19