Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9187. Min Range: -6.9187
Max Act: 6.8874. Min Act: -0.1700
Data Index: 6477591 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9187. Min Range: -6.9187
Max Act: 6.9187. Min Act: -0.1700
Data Index: 5428530 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9187. Min Range: -6.9187
Max Act: 6.7937. Min Act: -0.1700
Data Index: 996349 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9187. Min Range: -6.9187
Max Act: 6.7624. Min Act: -0.1700
Data Index: 6042636 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9187. Min Range: -6.9187
Max Act: 6.6999. Min Act: -0.1700
Data Index: 1301202 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9187. Min Range: -6.9187
Max Act: 6.6687. Min Act: -0.1700
Data Index: 1225543 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9187. Min Range: -6.9187
Max Act: 6.6687. Min Act: -0.1700
Data Index: 224594 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9187. Min Range: -6.9187
Max Act: 6.6687. Min Act: -0.1700
Data Index: 2983607 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9187. Min Range: -6.9187
Max Act: 6.6374. Min Act: -0.1700
Data Index: 7618668 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9187. Min Range: -6.9187
Max Act: 6.6374. Min Act: -0.1700
Data Index: 6667368 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9187. Min Range: -6.9187
Max Act: 6.6374. Min Act: -0.1700
Data Index: 2829639 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9187. Min Range: -6.9187
Max Act: 6.5749. Min Act: -0.1700
Data Index: 8263834 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9187. Min Range: -6.9187
Max Act: 6.5437. Min Act: -0.1700
Data Index: 1783710 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9187. Min Range: -6.9187
Max Act: 6.4812. Min Act: -0.1700
Data Index: 8187410 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9187. Min Range: -6.9187
Max Act: 6.5124. Min Act: -0.1700
Data Index: 3456485 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9187. Min Range: -6.9187
Max Act: 6.5124. Min Act: -0.1700
Data Index: 2726096 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9187. Min Range: -6.9187
Max Act: 6.4812. Min Act: -0.1700
Data Index: 3029736 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9187. Min Range: -6.9187
Max Act: 6.5124. Min Act: -0.1700
Data Index: 545524 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9187. Min Range: -6.9187
Max Act: 6.5124. Min Act: -0.1700
Data Index: 1783709 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9187. Min Range: -6.9187
Max Act: 6.4812. Min Act: -0.1700
Data Index: 1990810 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #19