Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1954 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 3.1410. Min Range: -3.1410
Max Act: 3.1410. Min Act: -0.1700
Data Index: 1106055 (C4 (Web Text))
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1410. Min Range: -3.1410
Max Act: 3.0780. Min Act: -0.1700
Data Index: 820275 (C4 (Web Text))
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1410. Min Range: -3.1410
Max Act: 3.0938. Min Act: -0.1700
Data Index: 739098 (C4 (Web Text))
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1410. Min Range: -3.1410
Max Act: 3.0938. Min Act: -0.1700
Data Index: 513740 (C4 (Web Text))
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1410. Min Range: -3.1410
Max Act: 3.0464. Min Act: -0.1700
Data Index: 1198887 (C4 (Web Text))
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1410. Min Range: -3.1410
Max Act: 3.0306. Min Act: -0.1700
Data Index: 82896 (C4 (Web Text))
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1410. Min Range: -3.1410
Max Act: 3.0306. Min Act: -0.1700
Data Index: 1185014 (C4 (Web Text))
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1410. Min Range: -3.1410
Max Act: 2.9990. Min Act: -0.1700
Data Index: 853395 (C4 (Web Text))
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1410. Min Range: -3.1410
Max Act: 2.9990. Min Act: -0.1700
Data Index: 768597 (C4 (Web Text))
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1410. Min Range: -3.1410
Max Act: 2.9832. Min Act: -0.1700
Data Index: 1261958 (C4 (Web Text))
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1410. Min Range: -3.1410
Max Act: 2.9674. Min Act: -0.1700
Data Index: 570060 (C4 (Web Text))
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1410. Min Range: -3.1410
Max Act: 2.9832. Min Act: -0.1700
Data Index: 1347855 (C4 (Web Text))
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1410. Min Range: -3.1410
Max Act: 2.9832. Min Act: -0.1700
Data Index: 530573 (C4 (Web Text))
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1410. Min Range: -3.1410
Max Act: 2.9357. Min Act: -0.1700
Data Index: 1082735 (C4 (Web Text))
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1410. Min Range: -3.1410
Max Act: 2.9199. Min Act: -0.1700
Data Index: 364394 (C4 (Web Text))
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1410. Min Range: -3.1410
Max Act: 2.9199. Min Act: -0.1700
Data Index: 486650 (C4 (Web Text))
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1410. Min Range: -3.1410
Max Act: 2.9040. Min Act: -0.1700
Data Index: 6858 (C4 (Web Text))
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1410. Min Range: -3.1410
Max Act: 2.9357. Min Act: -0.1700
Data Index: 54012 (C4 (Web Text))
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1410. Min Range: -3.1410
Max Act: 2.9199. Min Act: -0.1700
Data Index: 899246 (C4 (Web Text))
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1410. Min Range: -3.1410
Max Act: 2.9040. Min Act: -0.1700
Data Index: 343787 (C4 (Web Text))
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #19