Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2271 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4806. Min Range: -8.4806
Max Act: 8.4806. Min Act: -0.1700
Data Index: 4311791 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4806. Min Range: -8.4806
Max Act: 8.1681. Min Act: -0.1700
Data Index: 2147168 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4806. Min Range: -8.4806
Max Act: 7.9181. Min Act: -0.1700
Data Index: 1270249 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4806. Min Range: -8.4806
Max Act: 7.9493. Min Act: -0.1700
Data Index: 1626988 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4806. Min Range: -8.4806
Max Act: 7.8556. Min Act: -0.1700
Data Index: 1896409 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4806. Min Range: -8.4806
Max Act: 7.8243. Min Act: -0.1700
Data Index: 2453718 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4806. Min Range: -8.4806
Max Act: 7.8556. Min Act: -0.1700
Data Index: 169534 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4806. Min Range: -8.4806
Max Act: 7.7931. Min Act: -0.1700
Data Index: 211294 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4806. Min Range: -8.4806
Max Act: 7.7618. Min Act: -0.1700
Data Index: 3091406 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4806. Min Range: -8.4806
Max Act: 7.7931. Min Act: -0.1700
Data Index: 2696032 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4806. Min Range: -8.4806
Max Act: 7.7931. Min Act: -0.1700
Data Index: 4655228 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4806. Min Range: -8.4806
Max Act: 7.7618. Min Act: -0.1700
Data Index: 7242420 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4806. Min Range: -8.4806
Max Act: 7.7306. Min Act: -0.1700
Data Index: 3207964 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4806. Min Range: -8.4806
Max Act: 7.6993. Min Act: -0.1700
Data Index: 7706661 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4806. Min Range: -8.4806
Max Act: 7.6993. Min Act: -0.1700
Data Index: 4045611 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4806. Min Range: -8.4806
Max Act: 7.6368. Min Act: -0.1700
Data Index: 7736772 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4806. Min Range: -8.4806
Max Act: 7.6368. Min Act: -0.1700
Data Index: 3952426 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4806. Min Range: -8.4806
Max Act: 7.6368. Min Act: -0.1700
Data Index: 8427986 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4806. Min Range: -8.4806
Max Act: 7.6368. Min Act: -0.1700
Data Index: 1730905 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4806. Min Range: -8.4806
Max Act: 7.5743. Min Act: -0.1700
Data Index: 3051208 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #19