Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5465 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8570. Min Range: -2.8570
Max Act: 2.8570. Min Act: -0.1700
Data Index: 8526450 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8570. Min Range: -2.8570
Max Act: 2.7774. Min Act: -0.1700
Data Index: 185377 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8570. Min Range: -2.8570
Max Act: 2.7615. Min Act: -0.1700
Data Index: 4009114 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8570. Min Range: -2.8570
Max Act: 2.7615. Min Act: -0.1700
Data Index: 8301991 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8570. Min Range: -2.8570
Max Act: 2.7615. Min Act: -0.1700
Data Index: 2107485 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8570. Min Range: -2.8570
Max Act: 2.7455. Min Act: -0.1700
Data Index: 3420960 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8570. Min Range: -2.8570
Max Act: 2.7455. Min Act: -0.1700
Data Index: 5273330 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8570. Min Range: -2.8570
Max Act: 2.7295. Min Act: -0.1700
Data Index: 1625910 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8570. Min Range: -2.8570
Max Act: 2.7295. Min Act: -0.1700
Data Index: 2740089 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8570. Min Range: -2.8570
Max Act: 2.7136. Min Act: -0.1700
Data Index: 264672 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8570. Min Range: -2.8570
Max Act: 2.7136. Min Act: -0.1700
Data Index: 8699780 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8570. Min Range: -2.8570
Max Act: 2.7295. Min Act: -0.1700
Data Index: 7708719 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8570. Min Range: -2.8570
Max Act: 2.7136. Min Act: -0.1700
Data Index: 3422642 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8570. Min Range: -2.8570
Max Act: 2.7136. Min Act: -0.1700
Data Index: 3189216 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8570. Min Range: -2.8570
Max Act: 2.6976. Min Act: -0.1700
Data Index: 5872058 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8570. Min Range: -2.8570
Max Act: 2.6816. Min Act: -0.1700
Data Index: 4242610 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8570. Min Range: -2.8570
Max Act: 2.6816. Min Act: -0.1700
Data Index: 1412040 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8570. Min Range: -2.8570
Max Act: 2.6976. Min Act: -0.1700
Data Index: 1071669 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8570. Min Range: -2.8570
Max Act: 2.6976. Min Act: -0.1700
Data Index: 1319327 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8570. Min Range: -2.8570
Max Act: 2.6816. Min Act: -0.1700
Data Index: 4220449 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19