Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3621 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0200. Min Range: -6.0200
Max Act: 6.0200. Min Act: -0.1700
Data Index: 577867 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0200. Min Range: -6.0200
Max Act: 6.0200. Min Act: -0.1700
Data Index: 5057016 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0200. Min Range: -6.0200
Max Act: 5.9887. Min Act: -0.1700
Data Index: 2847797 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0200. Min Range: -6.0200
Max Act: 5.9262. Min Act: -0.1700
Data Index: 3229751 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0200. Min Range: -6.0200
Max Act: 5.8637. Min Act: -0.1700
Data Index: 6681716 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0200. Min Range: -6.0200
Max Act: 5.8637. Min Act: -0.1700
Data Index: 547967 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0200. Min Range: -6.0200
Max Act: 5.8012. Min Act: -0.1700
Data Index: 4740807 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0200. Min Range: -6.0200
Max Act: 5.7700. Min Act: -0.1700
Data Index: 120485 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0200. Min Range: -6.0200
Max Act: 5.7387. Min Act: -0.1700
Data Index: 1372794 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0200. Min Range: -6.0200
Max Act: 5.7387. Min Act: -0.1700
Data Index: 8227387 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0200. Min Range: -6.0200
Max Act: 5.7075. Min Act: -0.1700
Data Index: 5328843 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0200. Min Range: -6.0200
Max Act: 5.7075. Min Act: -0.1700
Data Index: 6600023 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0200. Min Range: -6.0200
Max Act: 5.7075. Min Act: -0.1700
Data Index: 6396078 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0200. Min Range: -6.0200
Max Act: 5.7075. Min Act: -0.1700
Data Index: 5778416 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0200. Min Range: -6.0200
Max Act: 5.6762. Min Act: -0.1700
Data Index: 5712597 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0200. Min Range: -6.0200
Max Act: 5.6762. Min Act: -0.1700
Data Index: 4907850 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0200. Min Range: -6.0200
Max Act: 5.6137. Min Act: -0.1700
Data Index: 6976570 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0200. Min Range: -6.0200
Max Act: 5.6450. Min Act: -0.1700
Data Index: 5190156 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0200. Min Range: -6.0200
Max Act: 5.6450. Min Act: -0.1700
Data Index: 3002864 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0200. Min Range: -6.0200
Max Act: 5.6450. Min Act: -0.1700
Data Index: 1949103 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #19