Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2228 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9134. Min Range: -4.9134
Max Act: 4.9134. Min Act: -0.1700
Data Index: 3611469 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9134. Min Range: -4.9134
Max Act: 4.8822. Min Act: -0.1700
Data Index: 7127704 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9134. Min Range: -4.9134
Max Act: 4.8509. Min Act: -0.1700
Data Index: 4113918 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9134. Min Range: -4.9134
Max Act: 4.8197. Min Act: -0.1700
Data Index: 8595000 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9134. Min Range: -4.9134
Max Act: 4.7572. Min Act: -0.1700
Data Index: 1783648 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9134. Min Range: -4.9134
Max Act: 4.7572. Min Act: -0.1700
Data Index: 3859127 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9134. Min Range: -4.9134
Max Act: 4.7259. Min Act: -0.1700
Data Index: 7835087 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9134. Min Range: -4.9134
Max Act: 4.7259. Min Act: -0.1700
Data Index: 5036035 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9134. Min Range: -4.9134
Max Act: 4.7259. Min Act: -0.1700
Data Index: 1067733 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9134. Min Range: -4.9134
Max Act: 4.6947. Min Act: -0.1700
Data Index: 4109230 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9134. Min Range: -4.9134
Max Act: 4.6634. Min Act: -0.1700
Data Index: 7475126 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9134. Min Range: -4.9134
Max Act: 4.6322. Min Act: -0.1700
Data Index: 6547184 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9134. Min Range: -4.9134
Max Act: 4.6322. Min Act: -0.1700
Data Index: 420214 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9134. Min Range: -4.9134
Max Act: 4.6009. Min Act: -0.1700
Data Index: 1524478 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9134. Min Range: -4.9134
Max Act: 4.6009. Min Act: -0.1700
Data Index: 2530972 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9134. Min Range: -4.9134
Max Act: 4.5697. Min Act: -0.1700
Data Index: 258735 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9134. Min Range: -4.9134
Max Act: 4.5697. Min Act: -0.1700
Data Index: 6962016 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9134. Min Range: -4.9134
Max Act: 4.5697. Min Act: -0.1700
Data Index: 4261919 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9134. Min Range: -4.9134
Max Act: 4.5697. Min Act: -0.1700
Data Index: 7388155 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9134. Min Range: -4.9134
Max Act: 4.5697. Min Act: -0.1700
Data Index: 7391890 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #19