Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3999 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0575. Min Range: -8.0575
Max Act: 8.0575. Min Act: -0.1700
Data Index: 3203854 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0575. Min Range: -8.0575
Max Act: 7.8075. Min Act: -0.1700
Data Index: 2581067 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0575. Min Range: -8.0575
Max Act: 7.6825. Min Act: -0.1700
Data Index: 4331758 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0575. Min Range: -8.0575
Max Act: 7.6200. Min Act: -0.1700
Data Index: 7632596 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0575. Min Range: -8.0575
Max Act: 7.5887. Min Act: -0.1700
Data Index: 2879211 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0575. Min Range: -8.0575
Max Act: 7.5575. Min Act: -0.1700
Data Index: 6319027 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0575. Min Range: -8.0575
Max Act: 7.5262. Min Act: -0.1700
Data Index: 3345774 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0575. Min Range: -8.0575
Max Act: 7.5262. Min Act: -0.1700
Data Index: 1381223 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0575. Min Range: -8.0575
Max Act: 7.5262. Min Act: -0.1700
Data Index: 567169 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0575. Min Range: -8.0575
Max Act: 7.4950. Min Act: -0.1700
Data Index: 6906527 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0575. Min Range: -8.0575
Max Act: 7.4950. Min Act: -0.1700
Data Index: 792781 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0575. Min Range: -8.0575
Max Act: 7.4950. Min Act: -0.1700
Data Index: 4325017 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0575. Min Range: -8.0575
Max Act: 7.4637. Min Act: -0.1700
Data Index: 4929796 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0575. Min Range: -8.0575
Max Act: 7.4637. Min Act: -0.1700
Data Index: 935372 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0575. Min Range: -8.0575
Max Act: 7.4637. Min Act: -0.1700
Data Index: 1419293 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0575. Min Range: -8.0575
Max Act: 7.4325. Min Act: -0.1700
Data Index: 970087 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0575. Min Range: -8.0575
Max Act: 7.4637. Min Act: -0.1700
Data Index: 5305732 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0575. Min Range: -8.0575
Max Act: 7.4012. Min Act: -0.1700
Data Index: 4554426 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0575. Min Range: -8.0575
Max Act: 7.3700. Min Act: -0.1700
Data Index: 32215 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0575. Min Range: -8.0575
Max Act: 7.3700. Min Act: -0.1700
Data Index: 619769 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #19