Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 338 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.5475. Min Range: -4.5475
Max Act: 4.5475. Min Act: -0.1700
Data Index: 1617641 (Python Code)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5475. Min Range: -4.5475
Max Act: 4.4850. Min Act: -0.1700
Data Index: 1474827 (Python Code)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5475. Min Range: -4.5475
Max Act: 4.3912. Min Act: -0.1700
Data Index: 1004033 (C4 (Web Text))
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5475. Min Range: -4.5475
Max Act: 4.3600. Min Act: -0.1699
Data Index: 1438190 (Python Code)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5475. Min Range: -4.5475
Max Act: 4.3912. Min Act: -0.1700
Data Index: 1515873 (Python Code)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5475. Min Range: -4.5475
Max Act: 4.3600. Min Act: -0.1700
Data Index: 1569748 (Python Code)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5475. Min Range: -4.5475
Max Act: 4.3287. Min Act: -0.1700
Data Index: 1464370 (Python Code)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5475. Min Range: -4.5475
Max Act: 4.3600. Min Act: -0.1700
Data Index: 1649218 (Python Code)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5475. Min Range: -4.5475
Max Act: 4.3600. Min Act: -0.1700
Data Index: 1381586 (Python Code)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5475. Min Range: -4.5475
Max Act: 4.3600. Min Act: -0.1700
Data Index: 1402938 (Python Code)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5475. Min Range: -4.5475
Max Act: 4.3287. Min Act: -0.1700
Data Index: 1435918 (Python Code)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5475. Min Range: -4.5475
Max Act: 4.3287. Min Act: -0.1700
Data Index: 1510808 (Python Code)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5475. Min Range: -4.5475
Max Act: 4.3600. Min Act: -0.1700
Data Index: 1378601 (Python Code)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5475. Min Range: -4.5475
Max Act: 4.2975. Min Act: -0.1700
Data Index: 1538631 (Python Code)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5475. Min Range: -4.5475
Max Act: 4.2662. Min Act: -0.1700
Data Index: 1479193 (Python Code)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5475. Min Range: -4.5475
Max Act: 4.2975. Min Act: -0.1700
Data Index: 1655911 (Python Code)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5475. Min Range: -4.5475
Max Act: 4.2662. Min Act: -0.1700
Data Index: 1407886 (Python Code)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5475. Min Range: -4.5475
Max Act: 4.2975. Min Act: -0.1700
Data Index: 1558810 (Python Code)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5475. Min Range: -4.5475
Max Act: 4.2350. Min Act: -0.1700
Data Index: 1384006 (Python Code)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5475. Min Range: -4.5475
Max Act: 4.2662. Min Act: -0.1700
Data Index: 1448149 (Python Code)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #19