Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 514 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2593. Min Range: -5.2593
Max Act: 5.2281. Min Act: -0.1699
Data Index: 4789910 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2593. Min Range: -5.2593
Max Act: 5.2593. Min Act: -0.1700
Data Index: 8780483 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2593. Min Range: -5.2593
Max Act: 5.1343. Min Act: -0.1700
Data Index: 5524485 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2593. Min Range: -5.2593
Max Act: 5.1343. Min Act: -0.1700
Data Index: 6679595 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2593. Min Range: -5.2593
Max Act: 5.1031. Min Act: -0.1700
Data Index: 854012 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2593. Min Range: -5.2593
Max Act: 5.1031. Min Act: -0.1699
Data Index: 6946935 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2593. Min Range: -5.2593
Max Act: 5.1031. Min Act: -0.1700
Data Index: 4607737 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2593. Min Range: -5.2593
Max Act: 5.1031. Min Act: -0.1700
Data Index: 6319165 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2593. Min Range: -5.2593
Max Act: 5.0718. Min Act: -0.1700
Data Index: 7154632 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2593. Min Range: -5.2593
Max Act: 5.0406. Min Act: -0.1700
Data Index: 8759792 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2593. Min Range: -5.2593
Max Act: 5.0406. Min Act: -0.1700
Data Index: 4732736 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2593. Min Range: -5.2593
Max Act: 5.0406. Min Act: -0.1700
Data Index: 4493591 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2593. Min Range: -5.2593
Max Act: 5.0093. Min Act: -0.1700
Data Index: 932691 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2593. Min Range: -5.2593
Max Act: 5.0406. Min Act: -0.1700
Data Index: 1703763 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2593. Min Range: -5.2593
Max Act: 5.0093. Min Act: -0.1700
Data Index: 7020767 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2593. Min Range: -5.2593
Max Act: 5.0406. Min Act: -0.1700
Data Index: 327242 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2593. Min Range: -5.2593
Max Act: 5.0093. Min Act: -0.1700
Data Index: 196170 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2593. Min Range: -5.2593
Max Act: 5.0093. Min Act: -0.1700
Data Index: 4213686 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2593. Min Range: -5.2593
Max Act: 5.0093. Min Act: -0.1700
Data Index: 8739951 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2593. Min Range: -5.2593
Max Act: 4.9781. Min Act: -0.1700
Data Index: 4653745 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #19