Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2165 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9982. Min Range: -3.9982
Max Act: 3.9670. Min Act: -0.1700
Data Index: 6119461 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9982. Min Range: -3.9982
Max Act: 3.9982. Min Act: -0.1700
Data Index: 8227378 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9982. Min Range: -3.9982
Max Act: 3.9357. Min Act: -0.1700
Data Index: 8195664 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9982. Min Range: -3.9982
Max Act: 3.9044. Min Act: -0.1700
Data Index: 1204345 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9982. Min Range: -3.9982
Max Act: 3.9670. Min Act: -0.1700
Data Index: 4866193 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9982. Min Range: -3.9982
Max Act: 3.9357. Min Act: -0.1700
Data Index: 981418 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9982. Min Range: -3.9982
Max Act: 3.9357. Min Act: -0.1700
Data Index: 8774937 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9982. Min Range: -3.9982
Max Act: 3.9044. Min Act: -0.1700
Data Index: 6577811 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9982. Min Range: -3.9982
Max Act: 3.9044. Min Act: -0.1700
Data Index: 7361043 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9982. Min Range: -3.9982
Max Act: 3.9044. Min Act: -0.1700
Data Index: 4998314 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9982. Min Range: -3.9982
Max Act: 3.9044. Min Act: -0.1700
Data Index: 2176494 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9982. Min Range: -3.9982
Max Act: 3.9044. Min Act: -0.1700
Data Index: 1916447 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9982. Min Range: -3.9982
Max Act: 3.9044. Min Act: -0.1700
Data Index: 5152731 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9982. Min Range: -3.9982
Max Act: 3.9044. Min Act: -0.1700
Data Index: 826968 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9982. Min Range: -3.9982
Max Act: 3.9044. Min Act: -0.1700
Data Index: 5468622 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9982. Min Range: -3.9982
Max Act: 3.9044. Min Act: -0.1700
Data Index: 5919321 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9982. Min Range: -3.9982
Max Act: 3.9044. Min Act: -0.1700
Data Index: 8622595 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9982. Min Range: -3.9982
Max Act: 3.9044. Min Act: -0.1700
Data Index: 1259516 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9982. Min Range: -3.9982
Max Act: 3.8732. Min Act: -0.1700
Data Index: 7686021 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9982. Min Range: -3.9982
Max Act: 3.8732. Min Act: -0.1700
Data Index: 3699748 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #19