Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3415 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4252. Min Range: -5.4252
Max Act: 5.4252. Min Act: -0.1700
Data Index: 1463013 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4252. Min Range: -5.4252
Max Act: 5.3940. Min Act: -0.1700
Data Index: 5634498 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4252. Min Range: -5.4252
Max Act: 5.2690. Min Act: -0.1700
Data Index: 5345433 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4252. Min Range: -5.4252
Max Act: 5.2065. Min Act: -0.1700
Data Index: 7744880 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4252. Min Range: -5.4252
Max Act: 5.2065. Min Act: -0.1700
Data Index: 6139328 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4252. Min Range: -5.4252
Max Act: 5.1752. Min Act: -0.1700
Data Index: 7702572 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4252. Min Range: -5.4252
Max Act: 5.1752. Min Act: -0.1700
Data Index: 4575406 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4252. Min Range: -5.4252
Max Act: 5.1440. Min Act: -0.1700
Data Index: 1814744 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4252. Min Range: -5.4252
Max Act: 5.1127. Min Act: -0.1700
Data Index: 2430468 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4252. Min Range: -5.4252
Max Act: 5.0815. Min Act: -0.1700
Data Index: 797346 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4252. Min Range: -5.4252
Max Act: 5.0502. Min Act: -0.1700
Data Index: 7192460 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4252. Min Range: -5.4252
Max Act: 5.0502. Min Act: -0.1700
Data Index: 6286217 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4252. Min Range: -5.4252
Max Act: 5.0502. Min Act: -0.1700
Data Index: 4049570 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4252. Min Range: -5.4252
Max Act: 5.0502. Min Act: -0.1700
Data Index: 908193 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4252. Min Range: -5.4252
Max Act: 5.0190. Min Act: -0.1700
Data Index: 6119833 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4252. Min Range: -5.4252
Max Act: 5.0190. Min Act: -0.1700
Data Index: 1262671 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4252. Min Range: -5.4252
Max Act: 4.9877. Min Act: -0.1700
Data Index: 1570636 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4252. Min Range: -5.4252
Max Act: 5.0502. Min Act: -0.1700
Data Index: 1031628 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4252. Min Range: -5.4252
Max Act: 5.0190. Min Act: -0.1700
Data Index: 7499500 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4252. Min Range: -5.4252
Max Act: 5.0190. Min Act: -0.1700
Data Index: 5533555 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #19