Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4654 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5434. Min Range: -7.5434
Max Act: 7.5434. Min Act: -0.1700
Data Index: 1280513 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5434. Min Range: -7.5434
Max Act: 7.4809. Min Act: -0.1700
Data Index: 3839156 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5434. Min Range: -7.5434
Max Act: 7.4184. Min Act: -0.1700
Data Index: 2053441 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5434. Min Range: -7.5434
Max Act: 7.3559. Min Act: -0.1700
Data Index: 8233108 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5434. Min Range: -7.5434
Max Act: 7.2934. Min Act: -0.1700
Data Index: 1852612 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5434. Min Range: -7.5434
Max Act: 7.2309. Min Act: -0.1700
Data Index: 1963688 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5434. Min Range: -7.5434
Max Act: 7.1059. Min Act: -0.1700
Data Index: 86265 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5434. Min Range: -7.5434
Max Act: 7.1684. Min Act: -0.1700
Data Index: 4580692 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5434. Min Range: -7.5434
Max Act: 7.1684. Min Act: -0.1699
Data Index: 4886263 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5434. Min Range: -7.5434
Max Act: 7.1684. Min Act: -0.1699
Data Index: 4743145 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5434. Min Range: -7.5434
Max Act: 7.1059. Min Act: -0.1700
Data Index: 3252939 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5434. Min Range: -7.5434
Max Act: 7.1059. Min Act: -0.1695
Data Index: 348194 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5434. Min Range: -7.5434
Max Act: 7.1059. Min Act: -0.1700
Data Index: 5506229 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5434. Min Range: -7.5434
Max Act: 7.1059. Min Act: -0.1700
Data Index: 5571707 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5434. Min Range: -7.5434
Max Act: 7.1059. Min Act: -0.1699
Data Index: 5742831 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5434. Min Range: -7.5434
Max Act: 7.1059. Min Act: -0.1699
Data Index: 6363508 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5434. Min Range: -7.5434
Max Act: 7.0434. Min Act: -0.1700
Data Index: 2344466 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5434. Min Range: -7.5434
Max Act: 7.0121. Min Act: -0.1699
Data Index: 8241338 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5434. Min Range: -7.5434
Max Act: 7.0434. Min Act: -0.1700
Data Index: 4836350 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5434. Min Range: -7.5434
Max Act: 7.0434. Min Act: -0.1700
Data Index: 5908852 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #19