Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5839 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5255. Min Range: -6.5255
Max Act: 6.5255. Min Act: -0.1700
Data Index: 3846384 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5255. Min Range: -6.5255
Max Act: 6.3380. Min Act: -0.1700
Data Index: 2092121 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5255. Min Range: -6.5255
Max Act: 6.2130. Min Act: -0.1700
Data Index: 6089959 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5255. Min Range: -6.5255
Max Act: 6.1817. Min Act: -0.1700
Data Index: 4515759 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5255. Min Range: -6.5255
Max Act: 6.1192. Min Act: -0.1700
Data Index: 2636856 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5255. Min Range: -6.5255
Max Act: 6.0255. Min Act: -0.1700
Data Index: 1965169 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5255. Min Range: -6.5255
Max Act: 6.0255. Min Act: -0.1700
Data Index: 8577627 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5255. Min Range: -6.5255
Max Act: 5.9942. Min Act: -0.1700
Data Index: 601648 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5255. Min Range: -6.5255
Max Act: 5.9317. Min Act: -0.1700
Data Index: 5119859 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5255. Min Range: -6.5255
Max Act: 5.8692. Min Act: -0.1700
Data Index: 7922042 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5255. Min Range: -6.5255
Max Act: 5.8692. Min Act: -0.1700
Data Index: 7050342 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5255. Min Range: -6.5255
Max Act: 5.8692. Min Act: -0.1700
Data Index: 5180581 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5255. Min Range: -6.5255
Max Act: 5.8692. Min Act: -0.1700
Data Index: 8406103 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5255. Min Range: -6.5255
Max Act: 5.9005. Min Act: -0.1700
Data Index: 4690407 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5255. Min Range: -6.5255
Max Act: 5.8380. Min Act: -0.1700
Data Index: 4620927 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5255. Min Range: -6.5255
Max Act: 5.8380. Min Act: -0.1700
Data Index: 8825655 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5255. Min Range: -6.5255
Max Act: 5.8067. Min Act: -0.1700
Data Index: 1643876 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5255. Min Range: -6.5255
Max Act: 5.8067. Min Act: -0.1700
Data Index: 3450969 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5255. Min Range: -6.5255
Max Act: 5.8067. Min Act: -0.1700
Data Index: 1951513 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5255. Min Range: -6.5255
Max Act: 5.8067. Min Act: -0.1700
Data Index: 8540773 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #19