Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2349 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9463. Min Range: -5.9463
Max Act: 5.9463. Min Act: -0.1700
Data Index: 1487642 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9463. Min Range: -5.9463
Max Act: 5.8526. Min Act: -0.1700
Data Index: 7597597 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9463. Min Range: -5.9463
Max Act: 5.7588. Min Act: -0.1700
Data Index: 6509840 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9463. Min Range: -5.9463
Max Act: 5.6338. Min Act: -0.1700
Data Index: 5403809 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9463. Min Range: -5.9463
Max Act: 5.6338. Min Act: -0.1700
Data Index: 6165444 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9463. Min Range: -5.9463
Max Act: 5.6026. Min Act: -0.1700
Data Index: 4056345 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9463. Min Range: -5.9463
Max Act: 5.5713. Min Act: -0.1700
Data Index: 8267187 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9463. Min Range: -5.9463
Max Act: 5.5401. Min Act: -0.1700
Data Index: 3326031 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9463. Min Range: -5.9463
Max Act: 5.5713. Min Act: -0.1700
Data Index: 1552846 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9463. Min Range: -5.9463
Max Act: 5.5401. Min Act: -0.1700
Data Index: 8780035 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9463. Min Range: -5.9463
Max Act: 5.4776. Min Act: -0.1700
Data Index: 8230805 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9463. Min Range: -5.9463
Max Act: 5.4776. Min Act: -0.1700
Data Index: 6198927 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9463. Min Range: -5.9463
Max Act: 5.4776. Min Act: -0.1700
Data Index: 8538126 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9463. Min Range: -5.9463
Max Act: 5.4463. Min Act: -0.1700
Data Index: 2301876 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9463. Min Range: -5.9463
Max Act: 5.4463. Min Act: -0.1700
Data Index: 2950262 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9463. Min Range: -5.9463
Max Act: 5.4463. Min Act: -0.1700
Data Index: 5491887 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9463. Min Range: -5.9463
Max Act: 5.4463. Min Act: -0.1700
Data Index: 4378970 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9463. Min Range: -5.9463
Max Act: 5.4151. Min Act: -0.1700
Data Index: 5245294 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9463. Min Range: -5.9463
Max Act: 5.4151. Min Act: -0.1700
Data Index: 3770648 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9463. Min Range: -5.9463
Max Act: 5.3838. Min Act: -0.1700
Data Index: 3392676 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #19