Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3524 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6330. Min Range: -5.6330
Max Act: 5.6330. Min Act: -0.1700
Data Index: 1638658 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6330. Min Range: -5.6330
Max Act: 5.3518. Min Act: -0.1700
Data Index: 4458746 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6330. Min Range: -5.6330
Max Act: 5.2580. Min Act: -0.1700
Data Index: 4811142 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6330. Min Range: -5.6330
Max Act: 5.2268. Min Act: -0.1700
Data Index: 973562 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6330. Min Range: -5.6330
Max Act: 5.1643. Min Act: -0.1700
Data Index: 727701 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6330. Min Range: -5.6330
Max Act: 5.1955. Min Act: -0.1700
Data Index: 3566209 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6330. Min Range: -5.6330
Max Act: 5.1955. Min Act: -0.1700
Data Index: 6934126 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6330. Min Range: -5.6330
Max Act: 5.1643. Min Act: -0.1700
Data Index: 779256 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6330. Min Range: -5.6330
Max Act: 5.1330. Min Act: -0.1700
Data Index: 8557577 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6330. Min Range: -5.6330
Max Act: 5.1330. Min Act: -0.1700
Data Index: 2461713 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6330. Min Range: -5.6330
Max Act: 5.1330. Min Act: -0.1700
Data Index: 7199191 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6330. Min Range: -5.6330
Max Act: 5.1018. Min Act: -0.1700
Data Index: 3568590 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6330. Min Range: -5.6330
Max Act: 5.1018. Min Act: -0.1700
Data Index: 3223087 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6330. Min Range: -5.6330
Max Act: 5.1018. Min Act: -0.1700
Data Index: 4863255 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6330. Min Range: -5.6330
Max Act: 5.0705. Min Act: -0.1700
Data Index: 2026427 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6330. Min Range: -5.6330
Max Act: 5.1330. Min Act: -0.1700
Data Index: 2151585 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6330. Min Range: -5.6330
Max Act: 5.1018. Min Act: -0.1700
Data Index: 5770034 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6330. Min Range: -5.6330
Max Act: 5.0393. Min Act: -0.1700
Data Index: 2321943 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6330. Min Range: -5.6330
Max Act: 5.0705. Min Act: -0.1700
Data Index: 6316280 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6330. Min Range: -5.6330
Max Act: 5.0705. Min Act: -0.1700
Data Index: 2063348 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #19