Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 400 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 3.3456. Min Range: -3.3456
Max Act: 3.3456. Min Act: -0.1700
Data Index: 1454130 (Python Code)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3456. Min Range: -3.3456
Max Act: 3.3142. Min Act: -0.1700
Data Index: 1506556 (Python Code)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3456. Min Range: -3.3456
Max Act: 3.3142. Min Act: -0.1700
Data Index: 1640802 (Python Code)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3456. Min Range: -3.3456
Max Act: 3.2985. Min Act: -0.1700
Data Index: 1548050 (Python Code)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3456. Min Range: -3.3456
Max Act: 3.2985. Min Act: -0.1700
Data Index: 1460758 (Python Code)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3456. Min Range: -3.3456
Max Act: 3.2985. Min Act: -0.1700
Data Index: 1490557 (Python Code)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3456. Min Range: -3.3456
Max Act: 3.2985. Min Act: -0.1700
Data Index: 1407146 (Python Code)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3456. Min Range: -3.3456
Max Act: 3.2670. Min Act: -0.1700
Data Index: 1614242 (Python Code)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3456. Min Range: -3.3456
Max Act: 3.2670. Min Act: -0.1700
Data Index: 1528393 (Python Code)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3456. Min Range: -3.3456
Max Act: 3.2356. Min Act: -0.1700
Data Index: 1456401 (Python Code)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3456. Min Range: -3.3456
Max Act: 3.2670. Min Act: -0.1700
Data Index: 1639265 (Python Code)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3456. Min Range: -3.3456
Max Act: 3.2356. Min Act: -0.1700
Data Index: 1488028 (Python Code)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3456. Min Range: -3.3456
Max Act: 3.2356. Min Act: -0.1700
Data Index: 1545148 (Python Code)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3456. Min Range: -3.3456
Max Act: 3.2199. Min Act: -0.1700
Data Index: 1566299 (Python Code)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3456. Min Range: -3.3456
Max Act: 3.2356. Min Act: -0.1700
Data Index: 1549690 (Python Code)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3456. Min Range: -3.3456
Max Act: 3.2199. Min Act: -0.1700
Data Index: 1567447 (Python Code)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3456. Min Range: -3.3456
Max Act: 3.2199. Min Act: -0.1700
Data Index: 1519125 (Python Code)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3456. Min Range: -3.3456
Max Act: 3.2199. Min Act: -0.1700
Data Index: 1437588 (Python Code)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3456. Min Range: -3.3456
Max Act: 3.2042. Min Act: -0.1700
Data Index: 1419488 (Python Code)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3456. Min Range: -3.3456
Max Act: 3.2042. Min Act: -0.1700
Data Index: 1446418 (Python Code)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #19