Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2821 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2561. Min Range: -6.2561
Max Act: 6.2561. Min Act: -0.1700
Data Index: 3866860 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2561. Min Range: -6.2561
Max Act: 6.1624. Min Act: -0.1700
Data Index: 4183689 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2561. Min Range: -6.2561
Max Act: 6.1311. Min Act: -0.1700
Data Index: 7055721 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2561. Min Range: -6.2561
Max Act: 6.0999. Min Act: -0.1700
Data Index: 8416180 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2561. Min Range: -6.2561
Max Act: 6.0999. Min Act: -0.1700
Data Index: 1187749 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2561. Min Range: -6.2561
Max Act: 6.0686. Min Act: -0.1700
Data Index: 7416130 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2561. Min Range: -6.2561
Max Act: 6.0374. Min Act: -0.1700
Data Index: 7761466 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2561. Min Range: -6.2561
Max Act: 6.0061. Min Act: -0.1700
Data Index: 560515 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2561. Min Range: -6.2561
Max Act: 6.0061. Min Act: -0.1700
Data Index: 4092023 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2561. Min Range: -6.2561
Max Act: 6.0061. Min Act: -0.1700
Data Index: 3171544 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2561. Min Range: -6.2561
Max Act: 5.9749. Min Act: -0.1700
Data Index: 2948368 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2561. Min Range: -6.2561
Max Act: 5.9436. Min Act: -0.1700
Data Index: 6582988 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2561. Min Range: -6.2561
Max Act: 5.9436. Min Act: -0.1700
Data Index: 1608319 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2561. Min Range: -6.2561
Max Act: 5.9124. Min Act: -0.1700
Data Index: 3722871 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2561. Min Range: -6.2561
Max Act: 5.9124. Min Act: -0.1700
Data Index: 5152656 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2561. Min Range: -6.2561
Max Act: 5.9124. Min Act: -0.1700
Data Index: 491740 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2561. Min Range: -6.2561
Max Act: 5.8811. Min Act: -0.1700
Data Index: 1930685 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2561. Min Range: -6.2561
Max Act: 5.9124. Min Act: -0.1700
Data Index: 6532940 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2561. Min Range: -6.2561
Max Act: 5.9124. Min Act: -0.1700
Data Index: 5821395 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2561. Min Range: -6.2561
Max Act: 5.8811. Min Act: -0.1700
Data Index: 5695998 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #19