Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3352 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8116. Min Range: -3.8116
Max Act: 3.8116. Min Act: -0.1700
Data Index: 1864763 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8116. Min Range: -3.8116
Max Act: 3.7334. Min Act: -0.1700
Data Index: 535079 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8116. Min Range: -3.8116
Max Act: 3.7022. Min Act: -0.1700
Data Index: 955450 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8116. Min Range: -3.8116
Max Act: 3.7178. Min Act: -0.1700
Data Index: 4010833 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8116. Min Range: -3.8116
Max Act: 3.6552. Min Act: -0.1700
Data Index: 7550346 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8116. Min Range: -3.8116
Max Act: 3.6396. Min Act: -0.1700
Data Index: 215488 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8116. Min Range: -3.8116
Max Act: 3.6552. Min Act: -0.1700
Data Index: 4572902 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8116. Min Range: -3.8116
Max Act: 3.6396. Min Act: -0.1700
Data Index: 3358398 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8116. Min Range: -3.8116
Max Act: 3.6083. Min Act: -0.1700
Data Index: 8092696 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8116. Min Range: -3.8116
Max Act: 3.6239. Min Act: -0.1700
Data Index: 1607029 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8116. Min Range: -3.8116
Max Act: 3.6083. Min Act: -0.1700
Data Index: 5252510 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8116. Min Range: -3.8116
Max Act: 3.6083. Min Act: -0.1700
Data Index: 3927062 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8116. Min Range: -3.8116
Max Act: 3.5926. Min Act: -0.1700
Data Index: 1901620 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8116. Min Range: -3.8116
Max Act: 3.5926. Min Act: -0.1700
Data Index: 5682905 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8116. Min Range: -3.8116
Max Act: 3.5926. Min Act: -0.1700
Data Index: 3481043 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8116. Min Range: -3.8116
Max Act: 3.5770. Min Act: -0.1700
Data Index: 2797465 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8116. Min Range: -3.8116
Max Act: 3.5770. Min Act: -0.1700
Data Index: 5149484 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8116. Min Range: -3.8116
Max Act: 3.5613. Min Act: -0.1700
Data Index: 5660304 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8116. Min Range: -3.8116
Max Act: 3.5613. Min Act: -0.1700
Data Index: 6617090 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8116. Min Range: -3.8116
Max Act: 3.5457. Min Act: -0.1700
Data Index: 6417495 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #19