Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3640 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2275. Min Range: -7.2275
Max Act: 7.2275. Min Act: -0.1700
Data Index: 3033451 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2275. Min Range: -7.2275
Max Act: 7.2275. Min Act: -0.1700
Data Index: 879485 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2275. Min Range: -7.2275
Max Act: 7.1962. Min Act: -0.1700
Data Index: 8633465 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2275. Min Range: -7.2275
Max Act: 7.1650. Min Act: -0.1700
Data Index: 2211284 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2275. Min Range: -7.2275
Max Act: 7.1650. Min Act: -0.1700
Data Index: 5732804 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2275. Min Range: -7.2275
Max Act: 7.1650. Min Act: -0.1700
Data Index: 4205515 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2275. Min Range: -7.2275
Max Act: 7.1337. Min Act: -0.1700
Data Index: 5839384 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2275. Min Range: -7.2275
Max Act: 7.1337. Min Act: -0.1700
Data Index: 834256 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2275. Min Range: -7.2275
Max Act: 7.1025. Min Act: -0.1700
Data Index: 7648573 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2275. Min Range: -7.2275
Max Act: 7.0712. Min Act: -0.1700
Data Index: 8645247 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2275. Min Range: -7.2275
Max Act: 7.0712. Min Act: -0.1700
Data Index: 2471264 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2275. Min Range: -7.2275
Max Act: 7.0400. Min Act: -0.1700
Data Index: 8053769 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2275. Min Range: -7.2275
Max Act: 7.0087. Min Act: -0.1700
Data Index: 7630075 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2275. Min Range: -7.2275
Max Act: 7.0087. Min Act: -0.1700
Data Index: 7890279 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2275. Min Range: -7.2275
Max Act: 7.0087. Min Act: -0.1700
Data Index: 1561056 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2275. Min Range: -7.2275
Max Act: 6.9775. Min Act: -0.1700
Data Index: 4347999 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2275. Min Range: -7.2275
Max Act: 6.9775. Min Act: -0.1700
Data Index: 5236377 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2275. Min Range: -7.2275
Max Act: 6.9775. Min Act: -0.1700
Data Index: 4474131 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2275. Min Range: -7.2275
Max Act: 7.0087. Min Act: -0.1700
Data Index: 2077561 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2275. Min Range: -7.2275
Max Act: 6.9462. Min Act: -0.1700
Data Index: 4600800 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #19